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. 19-RESID-POST-AA
    6. 84333
    Prev
    Next
    INDEX
    Explanations

    specialized

    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
     padd
    -0.07
    "';
    -0.06
     oo
    -0.06
     Gee
    -0.06
     Lup
    -0.06
     тради
    -0.06
     перей
    -0.06
    ап
    -0.06
     ";
    -0.06
    uted
    -0.06
    POSITIVE LOGITS
     specialized
    0.07
    =False
    0.06
    lb
    0.06
     femme
    0.06
     special
    0.06
    Special
    0.06
     hard
    0.06
     lacking
    0.06
    .roles
    0.06
    Dismiss
    0.06
    Activations Density 0.023%

    No Known Activations