© 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. 128783
    Prev
    Next
    INDEX
    Explanations

    landmarks/locations

    np_max-act · gemini-2.0-flash

    The neuron fires on capitalized proper‐noun place names (i.e. geographic location names).

    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
     nale
    -0.07
     wors
    -0.07
     stra
    -0.07
     EVEN
    -0.07
    oque
    -0.07
    acb
    -0.07
    CardBody
    -0.07
    dup
    -0.06
    idade
    -0.06
    uli
    -0.06
    POSITIVE LOGITS
     pathname
    0.07
    ）：
    0.07
    Vue
    0.06
    [G
    0.06
     [("
    0.06
    插
    0.06
    อป
    0.06
    .Metadata
    0.06
    422
    0.06
    艺
    0.05
    Activations Density 0.036%

    No Known Activations