© 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
    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. 77696
    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
    REFERENCES
    -0.07
    asio
    -0.07
     nilai
    -0.07
    ±ط
    -0.07
     fluores
    -0.06
    ��
    -0.06
     Electoral
    -0.06
     diffusion
    -0.06
    Immutable
    -0.06
     stochastic
    -0.06
    POSITIVE LOGITS
     уси
    0.07
    _NAMESPACE
    0.07
    :'.$
    0.07
    (Collection
    0.06
    .commit
    0.06
    (/^
    0.06
    tweets
    0.06
     bö
    0.06
     stemmed
    0.06
    exus
    0.06
    Activations Density 0.002%

    No Known Activations