© 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. 11-RESID-POST-AA
    11. 123311
    Prev
    Next
    INDEX
    Explanations

    a

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URT
    -0.06
     swinger
    -0.06
    umed
    -0.06
    itted
    -0.06
    دود
    -0.06
    WINDOWS
    -0.06
     shit
    -0.06
     confessed
    -0.06
    aji
    -0.06
     ties
    -0.06
    POSITIVE LOGITS
     becomes
    0.08
     зап
    0.07
    となり
    0.07
     Πα
    0.06
     pochop
    0.06
     получ
    0.06
     "}
    0.06
     sailors
    0.06
     Elon
    0.06
     제출
    0.06
    Activations Density 0.391%

    No Known Activations