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. 7-RESID-POST-AA
    6. 128922
    Prev
    Next
    INDEX
    Explanations

    mold

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rocks
    -0.07
     prosperous
    -0.07
    ystems
    -0.06
    ception
    -0.06
    Nb
    -0.06
     초기
    -0.06
    ジョ
    -0.06
    -rock
    -0.06
    (br
    -0.06
     φορ
    -0.06
    POSITIVE LOGITS
    .DialogResult
    0.07
    Choices
    0.07
     offshore
    0.07
    .localStorage
    0.06
     smack
    0.06
     molding
    0.06
    .exists
    0.06
    _SY
    0.06
     mold
    0.06
    IW
    0.06
    Activations Density 0.002%

    No Known Activations