© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56957
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on tokens indicating an origin marker—especially the preposition “from” in travel‐cost or route contexts.

    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
     aşağıdaki
    -0.06
     ними
    -0.06
     Chain
    -0.06
     Gast
    -0.06
     majors
    -0.06
     Ro
    -0.06
     occasionally
    -0.06
     مال
    -0.06
     Sh
    -0.06
     То
    -0.06
    POSITIVE LOGITS
    _estimators
    0.07
    =D
    0.07
    _values
    0.07
    *b
    0.07
    	constexpr
    0.07
    Billing
    0.06
    公里
    0.06
    ebx
    0.06
     IR
    0.06
    \xd
    0.06
    Activations Density 0.021%

    No Known Activations