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. 128896
    Prev
    Next
    INDEX
    Explanations

    to

    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
    .ENTER
    -0.07
    .more
    -0.07
    ятно
    -0.06
    INTERN
    -0.06
     орг
    -0.06
    .street
    -0.06
     prognosis
    -0.06
     tahmin
    -0.06
    .setTimeout
    -0.06
     recoil
    -0.06
    POSITIVE LOGITS
    Tests
    0.06
     Tên
    0.06
    _events
    0.06
     subdued
    0.06
     Cmd
    0.06
    PE
    0.06
     coronavirus
    0.06
     �
    0.06
    201
    0.06
     millones
    0.06
    Activations Density 0.001%

    No Known Activations