© 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. 35217
    Prev
    Next
    INDEX
    Explanations

    Label

    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
     Dos
    -0.07
    Rep
    -0.07
    과의
    -0.07
     sonra
    -0.07
    <D
    -0.06
     phase
    -0.06
     yanı
    -0.06
     take
    -0.06
    metrics
    -0.06
    	Type
    -0.06
    POSITIVE LOGITS
    ........
    0.07
    profit
    0.07
    xFFFFFFFF
    0.07
     portray
    0.06
     misdemean
    0.06
     objekt
    0.06
     телеф
    0.06
    classname
    0.06
    learner
    0.06
     sil
    0.06
    Activations Density 0.001%

    No Known Activations