© 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. 125131
    Prev
    Next
    INDEX
    Explanations

    insight

    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
     Nom
    -0.08
     permissible
    -0.07
     Dou
    -0.07
     voiture
    -0.07
     occurrence
    -0.07
     caratter
    -0.07
    _PUR
    -0.07
     terminology
    -0.07
    _Em
    -0.07
     realiz
    -0.07
    POSITIVE LOGITS
     insights
    0.09
     insight
    0.09
     Insights
    0.08
     profits
    0.08
     outsiders
    0.07
     insiders
    0.07
     Insight
    0.07
    益
    0.07
     ingl
    0.07
     insider
    0.07
    Activations Density 0.009%

    No Known Activations