© 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. 110254
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting descriptive modifiers of spatial orientation or variation—words like “different,” “vertical,” “horizontal,” etc.

    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
    Menus
    -0.06
    data
    -0.06
    Regarding
    -0.06
    bold
    -0.06
    _il
    -0.06
    อะ
    -0.06
    something
    -0.06
     peut
    -0.06
    ію
    -0.06
    BOARD
    -0.06
    POSITIVE LOGITS
     Placement
    0.07
    tap
    0.07
    /apache
    0.07
    odge
    0.07
     passive
    0.06
     expos
    0.06
    _OPENGL
    0.06
    ipple
    0.06
     excuse
    0.06
    peed
    0.06
    Activations Density 0.072%

    No Known Activations