© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 32643
    Prev
    Next
    INDEX
    Explanations

    :

    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
    ва
    -0.07
     VIII
    -0.07
    �
    -0.06
    env
    -0.06
     prepar
    -0.06
    dio
    -0.06
     tiempo
    -0.06
     字
    -0.06
    ENTE
    -0.06
    σου
    -0.06
    POSITIVE LOGITS
     systemFontOfSize
    0.07
     CompletableFuture
    0.07
     battled
    0.07
     благод
    0.06
     yönelik
    0.06
     globals
    0.06
     cancellationToken
    0.06
    directive
    0.06
     aşırı
    0.06
     retrieves
    0.06
    Activations Density 0.002%

    No Known Activations