© 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. 126264
    Prev
    Next
    INDEX
    Explanations

    traffic

    np_max-act · gemini-2.0-flash

    The neuron is specialized to activate on occurrences of the word “traffic” (in any context or casing).

    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
    .Rendering
    -0.07
    ožná
    -0.07
    WritableDatabase
    -0.07
    _end
    -0.07
    ζό
    -0.07
    22
    -0.07
    -install
    -0.06
     proporcion
    -0.06
    Set
    -0.06
    imeline
    -0.06
    POSITIVE LOGITS
     traffic
    0.16
     Traffic
    0.14
    traffic
    0.12
     traff
    0.09
    Traffic
    0.09
     motorists
    0.08
     tariff
    0.08
     trafficking
    0.08
     dealings
    0.07
    ff
    0.07
    Activations Density 0.007%

    No Known Activations