© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94764
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Peak
    -0.07
    threshold
    -0.07
     congestion
    -0.07
     clusters
    -0.07
     Reads
    -0.07
     considerations
    -0.06
     experiencing
    -0.06
    _glyph
    -0.06
    Drawing
    -0.06
    _iteration
    -0.06
    POSITIVE LOGITS
    language
    0.08
    Sau
    0.07
     Sau
    0.07
    gg
    0.06
     garant
    0.06
    /language
    0.06
    makt
    0.06
     interess
    0.06
    音楽
    0.06
    �
    0.06
    Activations Density 0.010%

    No Known Activations