Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 28974
    Prev
    Next
    INDEX
    Explanations

    s

    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
    suz
    -0.06
     pd
    -0.06
    bdd
    -0.06
     Wasser
    -0.06
    ++]
    -0.06
    CBC
    -0.06
    							  
    -0.06
    radan
    -0.06
     PhD
    -0.06
     consc
    -0.06
    POSITIVE LOGITS
    .Left
    0.07
    (print
    0.07
    (library
    0.07
    탕
    0.07
     окрем
    0.07
     difficulty
    0.07
    	rep
    0.06
    (Properties
    0.06
    ję
    0.06
    (split
    0.06
    Activations Density 0.000%

    No Known Activations