© 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. 15-RESID-POST-AA
    11. 9797
    Prev
    Next
    INDEX
    Explanations

    crisp

    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
     Його
    -0.08
    ування
    -0.07
     gdb
    -0.07
    capacity
    -0.07
    .stdout
    -0.07
     fight
    -0.07
    genus
    -0.06
    _arr
    -0.06
    .translate
    -0.06
     github
    -0.06
    POSITIVE LOGITS
     crisp
    0.08
    ples
    0.06
     알고
    0.06
     Comment
    0.06
     cookie
    0.06
     peel
    0.06
     Nev
    0.06
    ENE
    0.06
     parç
    0.06
    resh
    0.06
    Activations Density 0.005%

    No Known Activations