© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109333
    Prev
    Next
    INDEX
    Explanations

    velocity

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by occurrences of the term “velocity” (and closely related forms) in technical descriptions.

    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
     Commons
    -0.07
     catcher
    -0.07
    615
    -0.07
    ms
    -0.06
     fasta
    -0.06
     subtraction
    -0.06
     asker
    -0.06
    arn
    -0.06
    aph
    -0.06
     forb
    -0.06
    POSITIVE LOGITS
     velocity
    0.12
     Velocity
    0.11
    velocity
    0.10
     velocities
    0.09
    Vel
    0.08
    Speed
    0.08
    .velocity
    0.08
    Velocity
    0.08
     veloc
    0.08
    速度
    0.08
    Activations Density 0.006%

    No Known Activations