© 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. 92170
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Spit
    -0.06
     活
    -0.06
    /g
    -0.06
     최고
    -0.06
    oleon
    -0.06
    allows
    -0.06
     faulty
    -0.06
     了
    -0.06
    firebase
    -0.06
    (@
    -0.06
    POSITIVE LOGITS
    .tokenize
    0.06
    stre
    0.06
     شدند
    0.06
     مبار
    0.06
     tie
    0.06
    ibraries
    0.06
    _mE
    0.06
     Kunden
    0.06
    791
    0.06
    .union
    0.06
    Activations Density 0.096%

    No Known Activations