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. 100839
    Prev
    Next
    INDEX
    Explanations

    Connecticut

    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
     mad
    -0.07
    典
    -0.07
    娘
    -0.06
    มา
    -0.06
    orst
    -0.06
     Cheers
    -0.06
     melody
    -0.06
    泽
    -0.06
    <<"\
    -0.06
    農
    -0.06
    POSITIVE LOGITS
     Connecticut
    0.14
     CT
    0.10
     Ct
    0.08
     Conn
    0.07
     професси
    0.07
    gtest
    0.07
    icut
    0.07
     downloading
    0.07
    PTH
    0.07
    グ
    0.07
    Activations Density 0.006%

    No Known Activations