© 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. 15-RESID-POST-AA
    11. 108141
    Prev
    Next
    INDEX
    Explanations

    legal court documents

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icom
    -0.07
    ods
    -0.07
    Authorize
    -0.06
    �
    -0.06
     dictated
    -0.06
    	layer
    -0.06
    _de
    -0.06
    essa
    -0.06
     hacked
    -0.06
    esso
    -0.06
    POSITIVE LOGITS
    Falsy
    0.06
    .unsubscribe
    0.06
    轉
    0.06
     halk
    0.06
    희
    0.06
    '])↵↵↵
    0.06
     Lady
    0.06
    .youtube
    0.06
    '↵↵↵↵
    0.06
    шла
    0.06
    Activations Density 0.011%

    No Known Activations