© 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. 128727
    Prev
    Next
    INDEX
    Explanations

    raising and lowering

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting words that describe mechanical parts moving or reconfiguring (e.g. fold, swing, pivot, retractable).

    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
    _TIM
    -0.07
     fueled
    -0.07
     yaklaş
    -0.07
     rov
    -0.07
     atof
    -0.07
     mẽ
    -0.07
     shouts
    -0.07
    Israeli
    -0.06
     hồ
    -0.06
    wu
    -0.06
    POSITIVE LOGITS
     motivating
    0.07
     Oswald
    0.06
    .Java
    0.06
    CG
    0.06
     Lazy
    0.06
    Natural
    0.06
    _PROC
    0.06
    dealloc
    0.06
     Staples
    0.06
     Libraries
    0.06
    Activations Density 0.059%

    No Known Activations