© 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. 7-RESID-POST-AA
    11. 27494
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    VI
    -0.07
    zę
    -0.06
    aceutical
    -0.06
    ення
    -0.06
    ohana
    -0.06
     πρώτη
    -0.06
    vu
    -0.06
    νό
    -0.06
     CType
    -0.06
    	elif
    -0.06
    POSITIVE LOGITS
     Indicates
    0.07
     değiştir
    0.07
     salir
    0.07
    chars
    0.06
     ';↵↵
    0.06
    rawler
    0.06
    .TRUE
    0.06
    {
↵
↵
    0.06
     Brewer
    0.06
    (".",
    0.06
    Activations Density 0.025%

    No Known Activations