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. 88866
    Prev
    Next
    INDEX
    Explanations

    repetition in lists

    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
     capsule
    -0.06
    ipping
    -0.06
     BH
    -0.06
    acd
    -0.06
     подв
    -0.06
    wingConstants
    -0.06
     Buk
    -0.06
    Russia
    -0.06
    lift
    -0.06
     बड
    -0.06
    POSITIVE LOGITS
     relentless
    0.07
     kommt
    0.06
     recruited
    0.06
    ences
    0.06
    .HTTP
    0.06
    ịa
    0.06
    SENT
    0.06
        ↵    ↵    ↵    ↵
    0.06
    _framework
    0.06
    .ag
    0.06
    Activations Density 0.132%

    No Known Activations