© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 700
    Prev
    Next
    INDEX
    Explanations

    oil well formations

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of subterranean geological formations (e.g. “subterranean reservoir,” “strata”) indicating it detects references to underground rock layers or reservoirs.

    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
    istan
    -0.06
    Im
    -0.06
     murky
    -0.06
    `.`
    -0.06
    菜
    -0.06
    	code
    -0.06
    oc
    -0.06
    	RTHOOK
    -0.06
    edula
    -0.06
     металли
    -0.06
    POSITIVE LOGITS
    incer
    0.07
    liers
    0.06
     Flexible
    0.06
    -company
    0.06
    REDIS
    0.06
    _quick
    0.06
     vivastreet
    0.06
    getBody
    0.06
     Heidi
    0.06
     CUSTOM
    0.06
    Activations Density 0.012%

    No Known Activations