© 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. 15-RESID-POST-AA
    11. 19899
    Prev
    Next
    INDEX
    Explanations

    (y

    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
     Buster
    -0.07
     بازیگر
    -0.06
     rocking
    -0.06
    -have
    -0.06
     亚洲
    -0.06
    mentions
    -0.06
     Pier
    -0.06
    .uint
    -0.06
     Meaning
    -0.06
    Craft
    -0.06
    POSITIVE LOGITS
     queried
    0.07
    .postValue
    0.06
    ovíd
    0.06
    _relationship
    0.06
    ectors
    0.06
     factors
    0.06
     bibliography
    0.06
     kit
    0.06
    cripts
    0.06
    VERTISE
    0.06
    Activations Density 0.000%

    No Known Activations