© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 80476
    Prev
    Next
    INDEX
    Explanations

    hiring services

    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
    abant
    -0.06
     :
    -0.06
    ictim
    -0.06
     precinct
    -0.06
    userRepository
    -0.06
     систем
    -0.06
    .Authorization
    -0.06
     �
    -0.06
    赢
    -0.06
    ENCHMARK
    -0.06
    POSITIVE LOGITS
     profund
    0.07
     solution
    0.07
    níky
    0.07
    _OPER
    0.06
     SOLUTION
    0.06
    _HASH
    0.06
    _US
    0.06
    _av
    0.06
     mutableListOf
    0.06
     yogurt
    0.06
    Activations Density 0.149%

    No Known Activations