© 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. 55416
    Prev
    Next
    INDEX
    Explanations

    cookie settings

    np_max-act · gemini-2.0-flash

    The neuron detects warnings or statements about disabling cookies (or blocking/refusing them) causing limited or lost site functionality.

    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
    евых
    -0.08
    -em
    -0.06
     propName
    -0.06
    530
    -0.06
     Codable
    -0.06
    JNI
    -0.06
    oze
    -0.06
     بدن
    -0.06
     يج
    -0.06
    ières
    -0.06
    POSITIVE LOGITS
     Freedom
    0.06
    HAL
    0.06
    ้าน
    0.06
     Basketball
    0.06
    Go
    0.06
     bathroom
    0.06
     shin
    0.06
     Rohing
    0.06
     gratuits
    0.06
     Detroit
    0.06
    Activations Density 0.005%

    No Known Activations