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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 27-RESID-POST-AA
    6. 9234
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ранения
    -0.07
    Procedure
    -0.07
     sentir
    -0.06
     некоторые
    -0.06
     güven
    -0.06
    indir
    -0.06
     four
    -0.06
    sie
    -0.06
     enquanto
    -0.06
    (BigInteger
    -0.06
    POSITIVE LOGITS
    .Up
    0.07
    Symfony
    0.06
    Pot
    0.06
    丹
    0.06
    BX
    0.06
     옆
    0.06
     záb
    0.06
    orage
    0.06
    esterday
    0.06
    Bay
    0.06
    Activations Density 0.072%

    No Known Activations