© 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. 121746
    Prev
    Next
    INDEX
    Explanations

    winner

    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
    	param
    -0.07
     �
    -0.07
     controlId
    -0.07
     recursos
    -0.06
     Nous
    -0.06
     Mal
    -0.06
     ''.
    -0.06
    685
    -0.06
     diameter
    -0.06
     س
    -0.06
    POSITIVE LOGITS
     winner
    0.10
     winners
    0.07
    Demo
    0.06
    _threshold
    0.06
    fall
    0.06
     Winner
    0.06
    /stdc
    0.06
    .pen
    0.06
    winner
    0.06
    Penn
    0.06
    Activations Density 0.012%

    No Known Activations