© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 80035
    Prev
    Next
    INDEX
    Explanations

    Rare diseases and disorders

    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
    振り
    -0.08
    [o
    -0.07
    .ba
    -0.07
     frontend
    -0.07
     Sadece
    -0.06
     واقعی
    -0.06
    Beginning
    -0.06
     stroj
    -0.06
    .percent
    -0.06
     hue
    -0.06
    POSITIVE LOGITS
    İK
    0.08
     LAB
    0.06
     indicators
    0.06
    CHANT
    0.06
    _inode
    0.06
     richness
    0.06
     二
    0.06
    amespace
    0.06
    ={"
    0.06
    computed
    0.06
    Activations Density 0.044%

    No Known Activations