© 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. 8859
    Prev
    Next
    INDEX
    Explanations

    photography

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative, instruction‐style verbs (like “Use,” “Consider,” “Frame,” etc.) in photography tips, flagging command or how‐to directives.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     modules
    -0.07
     Regression
    -0.07
    Bubble
    -0.06
    ibe
    -0.06
     shadows
    -0.06
     pack
    -0.06
     bubble
    -0.06
     regression
    -0.06
     orch
    -0.06
    ák
    -0.06
    POSITIVE LOGITS
     GNU
    0.07
     Kov
    0.07
    _EOL
    0.06
     Пів
    0.06
     krb
    0.06
    Initializer
    0.06
    redirectTo
    0.06
     Jose
    0.06
    ;

↵
    0.06
    ้นท
    0.06
    Activations Density 0.015%

    No Known Activations