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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6125
    Prev
    Next
    INDEX
    Explanations

    identifier

    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
    'O
    -0.07
     Cox
    -0.07
     Co
    -0.07
     CO
    -0.07
    MQ
    -0.07
     phases
    -0.06
     NC
    -0.06
    .CO
    -0.06
     wel
    -0.06
     reaches
    -0.06
    POSITIVE LOGITS
     identifier
    0.13
    Identifier
    0.10
    identifier
    0.10
     identifiers
    0.10
     Identifier
    0.07
    WithIdentifier
    0.07
    Locator
    0.07
    (withIdentifier
    0.07
    _SIGNAL
    0.07
     hashtags
    0.07
    Activations Density 0.006%

    No Known Activations