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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105274
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron detects “for each …” style list-iteration instructions asking to perform an action on each item.

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

    statements related to mathematical claims and their proofs.

    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
    ساب
    -0.07
     scanning
    -0.06
    Normals
    -0.06
     ｜
    -0.06
     دنی
    -0.06
    rezent
    -0.06
    ρή
    -0.06
    luet
    -0.06
     Περ
    -0.06
     Collider
    -0.06
    POSITIVE LOGITS
    shi
    0.07
     över
    0.06
    ेर
    0.06
     ister
    0.06
    ediální
    0.06
    /photo
    0.06
     الأسر
    0.06
     oci
    0.06
    ाई
    0.06
    ind
    0.06
    Activations Density 0.021%

    No Known Activations