© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56785
    Prev
    Next
    INDEX
    Explanations

    Duality/Similarity

    np_max-act · gemini-2.0-flash

    Neuron 4 fires on explicit binary-quantifier cues—especially the word “both” (and related tokens like the numeral “2”) indicating two‐item conjunctions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    questions related to identity verification and security measures in a digital context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Asset
    -0.06
    10
    -0.06
     tiện
    -0.06
    	height
    -0.06
    _terms
    -0.06
     Sports
    -0.06
    belongsTo
    -0.06
    speech
    -0.06
     dismissal
    -0.06
    lemn
    -0.06
    POSITIVE LOGITS
     ли
    0.06
    μιλος
    0.06
    ества
    0.06
     BCH
    0.06
     truly
    0.06
    ivia
    0.06
    стин
    0.06
     london
    0.06
    วโม
    0.06
    /location
    0.06
    Activations Density 0.062%

    No Known Activations