© 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. 19-RESID-POST-AA
    11. 111761
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    424
    -0.07
     singly
    -0.06
     samen
    -0.06
     weer
    -0.06
     gen
    -0.06
    WAR
    -0.06
     soup
    -0.06
    $url
    -0.06
     towns
    -0.06
     lon
    -0.06
    POSITIVE LOGITS
     Microsoft
    0.12
    Microsoft
    0.09
    swift
    0.09
    itbart
    0.07
     invert
    0.07
    ?>/
    0.07
     ASTM
    0.07
    }`).
    0.07
     MIT
    0.07
    >')
    0.07
    Activations Density 0.008%

    No Known Activations