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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 84782
    Prev
    Next
    INDEX
    Explanations

    back side

    np_max-act · gemini-2.0-flash

    descriptions and details related to semiconductor technology and packaging.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of a component’s back or rear side (e.g. “back side,” “rear surface”) in the text.

    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
    (昭和
    -0.07
    858
    -0.07
    totals
    -0.07
    Certainly
    -0.06
    rak
    -0.06
     competit
    -0.06
     probabilities
    -0.06
     circles
    -0.06
     Folder
    -0.06
     disk
    -0.06
    POSITIVE LOGITS
     Bates
    0.06
    HER
    0.06
    .expand
    0.06
    /~
    0.06
    /l
    0.06
     innate
    0.06
     insulting
    0.06
    /es
    0.06
     ResponseEntity
    0.06
     pnl
    0.06
    Activations Density 0.014%

    No Known Activations