Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85911
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of a geographic pass or “gap” in a mountain or ridge.

    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
     wrestlers
    -0.06
     debated
    -0.06
     blades
    -0.06
     IPL
    -0.06
     guild
    -0.06
    Versions
    -0.06
     Texture
    -0.06
     ця
    -0.06
    -effects
    -0.05
     TZ
    -0.05
    POSITIVE LOGITS
    百
    0.06
     говорит
    0.06
     gridSize
    0.06
    _SRV
    0.06
    important
    0.06
    .alignment
    0.06
    ently
    0.06
    그러
    0.06
    //}↵↵
    0.06
    wend
    0.06
    Activations Density 0.072%

    No Known Activations