© 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. 19-RESID-POST-AA
    6. 45701
    Prev
    Next
    INDEX
    Explanations

    In

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     railroad
    -0.07
    "D
    -0.06
    γι
    -0.06
     kuru
    -0.06
     Cooke
    -0.06
    _PO
    -0.06
     harm
    -0.06
    顔
    -0.06
     DATE
    -0.06
    ζ
    -0.06
    POSITIVE LOGITS
    txn
    0.07
    ats
    0.06
     ];
    0.06
    abby
    0.06
     имени
    0.06
    checks
    0.06
    -six
    0.06
    atten
    0.06
    _intf
    0.06
    apeutics
    0.06
    Activations Density 0.033%

    No Known Activations