© 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. 126156
    Prev
    Next
    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “source code” being publicly available or open for modification—that is, references to open‐source software.

    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
    esture
    -0.06
    番号
    -0.06
     PMID
    -0.06
     duty
    -0.06
     hypertension
    -0.06
     Cyc
    -0.06
     seront
    -0.06
    _glyph
    -0.06
    TypeName
    -0.06
     dubious
    -0.05
    POSITIVE LOGITS
    žel
    0.07
    ucursal
    0.07
     WX
    0.07
    _CL
    0.07
     Er
    0.07
    _SK
    0.07
     resonate
    0.07
    ารถ
    0.06
    aceutical
    0.06
     drummer
    0.06
    Activations Density 0.005%

    No Known Activations