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. 94220
    Prev
    Next
    INDEX
    Explanations

    General English language

    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
    equipment
    -0.07
     основных
    -0.07
    었다
    -0.07
    edis
    -0.06
    」と
    -0.06
    .test
    -0.06
    (Item
    -0.06
    _gap
    -0.06
    сл
    -0.06
     forcefully
    -0.06
    POSITIVE LOGITS
    ă
    0.07
    ț
    0.07
     αυτό
    0.07
    ultural
    0.06
     ori
    0.06
    .speed
    0.06
     și
    0.06
     cuối
    0.06
     ppl
    0.06
     hairstyles
    0.06
    Activations Density 0.072%

    No Known Activations