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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 36147
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Flynn
    -0.06
    .mapping
    -0.06
    Ops
    -0.06
     sur
    -0.06
     slož
    -0.06
    192
    -0.06
     Believe
    -0.06
     CSS
    -0.06
     "../../../
    -0.06
     paved
    -0.06
    POSITIVE LOGITS
    imeInterval
    0.07
     لـ
    0.07
     WaitForSeconds
    0.07
    anco
    0.07
    ursos
    0.06
     départ
    0.06
     розвиток
    0.06
    ото
    0.06
     natur
    0.06
    .duration
    0.06
    Activations Density 0.167%

    No Known Activations