© 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. 11-RESID-POST-AA
    11. 72795
    Prev
    Next
    INDEX
    Explanations

    setting variables

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WHY
    -0.07
    ΟΥ
    -0.06
    aternity
    -0.06
    ір
    -0.06
     fairness
    -0.06
    .readValue
    -0.06
    edral
    -0.06
    (regex
    -0.06
    Translate
    -0.06
    <lemma
    -0.06
    POSITIVE LOGITS
     ongoing
    0.07
     intellectuals
    0.07
    	mysqli
    0.06
    silver
    0.06
    และส
    0.06
     बढ
    0.06
     То
    0.06
     fen
    0.06
    xad
    0.06
    Regards
    0.06
    Activations Density 0.017%

    No Known Activations