Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93122
    Prev
    Next
    INDEX
    Explanations

    greater than

    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_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
     BET
    -0.06
    NonNull
    -0.06
    embali
    -0.06
    ,key
    -0.06
    .formData
    -0.06
     mercenaries
    -0.06
    iset
    -0.06
    Fake
    -0.06
    BigInteger
    -0.06
    (||
    -0.06
    POSITIVE LOGITS
     أد
    0.07
    opers
    0.06
     tied
    0.06
     نصب
    0.06
     πέ
    0.06
    .ToList
    0.06
     وا
    0.06
    232
    0.06
     diagnostics
    0.06
    /db
    0.06
    Activations Density 0.020%

    No Known Activations