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. 11-RESID-POST-AA
    6. 123849
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Critical
    -0.06
    三三
    -0.06
    RequestParam
    -0.06
     hazards
    -0.06
    FFFFFF
    -0.06
    .ep
    -0.06
    ▋▋
    -0.06
     olive
    -0.06
     proxies
    -0.06
    şehir
    -0.06
    POSITIVE LOGITS
    _cu
    0.06
     велик
    0.06
    intersection
    0.06
    AMI
    0.06
     axs
    0.06
    ypsum
    0.06
     Kra
    0.06
    Dal
    0.06
     побед
    0.06
     $("
    0.06
    Activations Density 0.013%

    No Known Activations