© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109238
    Prev
    Next
    INDEX
    Explanations

    Locations and directions

    np_max-act · gemini-2.0-flash

    The neuron primarily detects references to spatial location and distance (e.g., terms like “blocks,” “away,” street and road 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
    _google
    -0.07
     orange
    -0.07
     Stir
    -0.07
    -sheet
    -0.07
     Oyun
    -0.06
     Philosoph
    -0.06
     walkers
    -0.06
    Green
    -0.06
     NVIDIA
    -0.06
    とも
    -0.06
    POSITIVE LOGITS
    VES
    0.07
    uede
    0.07
    Nested
    0.06
     fontWithName
    0.06
     Lastly
    0.06
     DISTRIBUT
    0.06
    ignment
    0.06
     ServiceException
    0.06
    .Pixel
    0.06
    ?>/
    0.06
    Activations Density 0.030%

    No Known Activations