© 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. 93423
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Lod
    -0.06
    “No
    -0.06
     créer
    -0.06
    	Field
    -0.06
    птом
    -0.06
    _lo
    -0.06
     necessário
    -0.06
    Pass
    -0.06
    No
    -0.06
    <Input
    -0.06
    POSITIVE LOGITS
     blank
    0.08
    (offset
    0.08
     authenticated
    0.06
    PNG
    0.06
     concess
    0.06
    éo
    0.06
    生
    0.06
    "...
    0.06
    μος
    0.06
    pairs
    0.06
    Activations Density 0.054%

    No Known Activations