© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 31973
    Prev
    Next
    INDEX
    Explanations

    (void

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numerical
    -0.07
    	SC
    -0.07
    婆
    -0.06
    filepath
    -0.06
    filePath
    -0.06
     gest
    -0.06
     TL
    -0.06
    steder
    -0.06
    liste
    -0.06
    Non
    -0.06
    POSITIVE LOGITS
    (void
    0.09
    _TREE
    0.07
    _OID
    0.07
    ArgumentNullException
    0.06
    -nine
    0.06
    uddenly
    0.06
    _td
    0.06
     وقت
    0.06
    ernals
    0.06
    赢
    0.06
    Activations Density 0.001%

    No Known Activations