© 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. 129957
    Prev
    Next
    INDEX
    Explanations

    Harry Potter

    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
    _setting
    -0.08
     convin
    -0.06
    statt
    -0.06
     Cincinnati
    -0.06
    WithMany
    -0.06
    MetaData
    -0.06
    .Html
    -0.06
    ีผ
    -0.06
     Andersen
    -0.06
     (*((
    -0.06
    POSITIVE LOGITS
    ño
    0.06
     ejac
    0.06
    iscing
    0.06
    oko
    0.06
     clf
    0.06
    rna
    0.06
    wow
    0.06
    zing
    0.06
    onu
    0.06
     handle
    0.06
    Activations Density 0.004%

    No Known Activations