Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 619
    Prev
    Next
    INDEX
    Explanations

    Software/Technical Contexts

    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
     ingr
    -0.07
     genre
    -0.07
    .travel
    -0.06
    ;?>↵
    -0.06
    Print
    -0.06
    еком
    -0.06
    _base
    -0.06
    _ROM
    -0.06
    _published
    -0.06
    ("
    -0.06
    POSITIVE LOGITS
    entialAction
    0.07
     Bristol
    0.07
     mour
    0.06
    devil
    0.06
    あり
    0.06
    (intent
    0.06
     Antarctica
    0.06
    kop
    0.06
     ls
    0.06
     Catalonia
    0.06
    Activations Density 0.027%

    No Known Activations