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. 22269
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ricanes
    -0.07
     newborn
    -0.07
    LAB
    -0.07
    .tight
    -0.06
    _rho
    -0.06
    (thing
    -0.06
    jours
    -0.06
     infile
    -0.06
    -sp
    -0.06
    ındır
    -0.06
    POSITIVE LOGITS
    .Model
    0.06
     Laugh
    0.06
     subsidiary
    0.06
     giữ
    0.06
     Nikola
    0.06
    -MM
    0.06
     ز
    0.06
     advised
    0.06
     remember
    0.06
     Authorized
    0.06
    Activations Density 0.036%

    No Known Activations