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. 11-RESID-POST-AA
    6. 80925
    Prev
    Next
    INDEX
    Explanations

    sports categories in worldwide games

    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
     iii
    -0.06
     Poland
    -0.06
    ’in
    -0.06
    'in
    -0.06
     alph
    -0.06
    šší
    -0.06
    Jim
    -0.06
     idx
    -0.06
    OVÁ
    -0.06
     suis
    -0.06
    POSITIVE LOGITS
    &oacute
    0.06
    說
    0.06
     ActivityCompat
    0.06
    civil
    0.06
     Armed
    0.06
     норм
    0.06
    ��
    0.06
     recibir
    0.06
     COURT
    0.06
    fighters
    0.06
    Activations Density 0.003%

    No Known Activations