© 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. 30513
    Prev
    Next
    INDEX
    Explanations

    rotate

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of mechanical rotation—words describing parts turning or rotating around an axis.

    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
    检测
    -0.06
     storage
    -0.06
     tomato
    -0.06
     damping
    -0.05
     �
    -0.05
     Peru
    -0.05
    fen
    -0.05
     리
    -0.05
    浅
    -0.05
     tarea
    -0.05
    POSITIVE LOGITS
    .Popen
    0.07
    MASK
    0.07
     CENT
    0.07
    =find
    0.07
     основных
    0.07
    abcdef
    0.07
    ,number
    0.07
     concentr
    0.07
    owing
    0.07
    OptionsItemSelected
    0.07
    Activations Density 0.016%

    No Known Activations