© 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. 88983
    Prev
    Next
    INDEX
    Explanations

    data and code

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the model’s knowledge‐cutoff or training‐data cutoff date.

    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
     cure
    -0.06
    _running
    -0.06
     chicks
    -0.06
     clip
    -0.06
    /uploads
    -0.06
     mob
    -0.06
     ringing
    -0.06
    ל
    -0.06
     torn
    -0.06
    _profile
    -0.06
    POSITIVE LOGITS
    ,—
    0.07
    (path
    0.07
    ných
    0.06
    Dur
    0.06
     getUrl
    0.06
    qrt
    0.06
     energie
    0.06
    	Event
    0.06
    =forms
    0.06
    lated
    0.06
    Activations Density 0.057%

    No Known Activations