© 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. 70516
    Prev
    Next
    INDEX
    Explanations

    table, play, and other languages

    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
    prediction
    -0.06
    illion
    -0.06
    omes
    -0.06
    ORE
    -0.06
     záznam
    -0.06
     Michael
    -0.06
    ores
    -0.06
     энерг
    -0.06
    iao
    -0.06
    سته
    -0.06
    POSITIVE LOGITS
    -alist
    0.07
     παρ
    0.06
     moot
    0.06
     Dagger
    0.06
    効
    0.06
     toll
    0.06
    横
    0.06
    .Stage
    0.06
     konus
    0.06
     Implicit
    0.06
    Activations Density 0.094%

    No Known Activations