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. 128740
    Prev
    Next
    INDEX
    Explanations

    involved

    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
    CHOOL
    -0.07
    Experiment
    -0.07
     prey
    -0.07
     Days
    -0.06
     TREE
    -0.06
    Exercise
    -0.06
     infantry
    -0.06
    cích
    -0.06
    oki
    -0.06
    school
    -0.06
    POSITIVE LOGITS
     mě
    0.06
    /lab
    0.06
    ALCHEMY
    0.06
     prise
    0.06
     İzmir
    0.06
    favor
    0.06
    .compress
    0.06
    lacağ
    0.06
    ';";↵
    0.06
    nage
    0.06
    Activations Density 0.092%

    No Known Activations