© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91505
    Prev
    Next
    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash

    The neuron detects words expressing calls to support or urging action (e.g., Spanish imperatives like “apoye”).

    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
    elden
    -0.06
    risk
    -0.06
     Warranty
    -0.06
     Trad
    -0.06
     Perf
    -0.06
    _loading
    -0.06
     etk
    -0.06
     reinterpret
    -0.06
     Funktion
    -0.06
     berk
    -0.06
    POSITIVE LOGITS
     support
    0.10
     SUPPORT
    0.09
     doubly
    0.08
    _UINT
    0.08
     Support
    0.08
     staunch
    0.07
     opposes
    0.07
     좀
    0.07
    援
    0.07
    ุม
    0.07
    Activations Density 0.030%

    No Known Activations