© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 54368
    Prev
    Next
    INDEX
    Explanations

    shaft

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     packageName
    -0.07
    .Green
    -0.06
     Oz
    -0.06
     cel
    -0.06
    Tex
    -0.06
    ographies
    -0.06
    Look
    -0.06
    print
    -0.06
     teplot
    -0.06
    ंघ
    -0.05
    POSITIVE LOGITS
     shaft
    0.09
    ύτε
    0.07
     Sevent
    0.07
    .Se
    0.07
     clauses
    0.07
     executable
    0.07
     Seattle
    0.06
    secs
    0.06
    educ
    0.06
     misconduct
    0.06
    Activations Density 0.007%

    No Known Activations