© 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. 39770
    Prev
    Next
    INDEX
    Explanations

    non-english text

    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
     ragaz
    -0.08
     prá
    -0.07
     Streams
    -0.07
     переш
    -0.07
     rear
    -0.07
     pricey
    -0.07
    ráci
    -0.06
     prospective
    -0.06
     three
    -0.06
     Petro
    -0.06
    POSITIVE LOGITS
     donde
    0.07
     où
    0.07
    dıktan
    0.07
    Cause
    0.07
     onde
    0.06
    (et
    0.06
     где
    0.06
    GMT
    0.06
     Amendment
    0.06
     usa
    0.06
    Activations Density 0.016%

    No Known Activations