© 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. 7-RESID-POST-AA
    11. 53629
    Prev
    Next
    INDEX
    Explanations

    stroke

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _polygon
    -0.08
    _KP
    -0.07
     переш
    -0.07
    Mutex
    -0.06
    mux
    -0.06
     PyTuple
    -0.06
    _PARAM
    -0.06
    _EX
    -0.06
     ComboBox
    -0.06
    {id
    -0.06
    POSITIVE LOGITS
     stroke
    0.15
     strokes
    0.12
     Stroke
    0.12
     Stokes
    0.11
    stroke
    0.10
    Stroke
    0.09
     stro
    0.08
     �
    0.08
    -strokes
    0.08
    roke
    0.08
    Activations Density 0.005%

    No Known Activations