© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    export

    np_max-act · gemini-2.0-flash

    The neuron is picking up on numeric export‐related figures and metrics (e.g., decimal values tied to "exports," quantities, and countries).

    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
     Exped
    -0.07
     objs
    -0.06
    Evaluator
    -0.06
     sqr
    -0.06
    Record
    -0.06
    /location
    -0.06
     какие
    -0.06
     becoming
    -0.06
     purification
    -0.06
     formation
    -0.06
    POSITIVE LOGITS
    dates
    0.08
     więc
    0.06
    flip
    0.06
     Counts
    0.06
    ukkit
    0.06
    DAQ
    0.06
     option
    0.06
     GTK
    0.06
     {-
    0.06
    __',
    0.06
    Activations Density 0.009%

    No Known Activations