© 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. 15-RESID-POST-AA
    6. 103411
    Prev
    Next
    INDEX
    Explanations

    numerical reports

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allan
    -0.07
    339
    -0.07
     subtly
    -0.07
    .mi
    -0.06
     overhe
    -0.06
     ين
    -0.06
     boldly
    -0.06
    Datas
    -0.06
    /dd
    -0.06
    .ship
    -0.06
    POSITIVE LOGITS
    бит
    0.07
     creations
    0.07
     Serialization
    0.07
     پرونده
    0.06
     vai
    0.06
    谱
    0.06
    equals
    0.06
    خصوص
    0.06
    laştır
    0.06
     champs
    0.06
    Activations Density 0.117%

    No Known Activations