© 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. 126674
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron never actually activates on any token—i.e. it’s effectively “dead” and doesn’t detect any specific pattern.

    oai_token-act-pair · o4-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
    OTH
    -0.07
    —"
    -0.07
    cannot
    -0.07
    、「
    -0.07
    ();
↵
↵
↵
    -0.06
     mentally
    -0.06
     Born
    -0.06
    comment
    -0.06
    ồng
    -0.06
     volunteered
    -0.06
    POSITIVE LOGITS
     유
    0.07
     Tage
    0.07
     lavender
    0.06
     './../
    0.06
     ir
    0.06
     vår
    0.06
     дерева
    0.06
    olicited
    0.06
     republik
    0.06
    Backdrop
    0.06
    Activations Density 0.005%

    No Known Activations