© 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. 126707
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    np_max-act · gemini-2.0-flash

    This neuron activates on specialized nuclear‐/particle‐physics collision terminology—especially mentions of nuclei, ions, and heavy‐ion collision contexts.

    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
    迅
    -0.07
    Lin
    -0.06
     Plzeň
    -0.06
     vlan
    -0.06
     niece
    -0.06
     Gry
    -0.06
    ake
    -0.06
    .Entry
    -0.06
    _way
    -0.06
    thumbs
    -0.06
    POSITIVE LOGITS
     compressed
    0.07
    _serializer
    0.06
     BAL
    0.06
    .Def
    0.06
     dictator
    0.06
     multi
    0.06
    Css
    0.06
    isory
    0.06
    .Has
    0.06
    ovable
    0.06
    Activations Density 0.002%

    No Known Activations