© 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. 3-RESID-POST-AA
    11. 95276
    Prev
    Next
    INDEX
    Explanations

    line

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    虎
    -0.06
    .Interop
    -0.06
    Browsable
    -0.06
    Behaviour
    -0.06
    ==="
    -0.06
    _repository
    -0.06
    _Part
    -0.06
    istinguish
    -0.06
    \Collections
    -0.06
    ในว
    -0.06
    POSITIVE LOGITS
    ->_
    0.13
    ::$
    0.13
    ITS
    0.07
     threaten
    0.07
     Behind
    0.07
     conflicts
    0.06
     convicted
    0.06
     ข
    0.06
     $_
    0.06
     begins
    0.06
    Activations Density 0.002%

    No Known Activations