© 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. 89091
    Prev
    Next
    INDEX
    Explanations

    money and power

    np_max-act · gemini-2.0-flash

    This neuron fires on words that describe supplying or using energy—e.g. “power,” “fuel,” or “support” in an energy context.

    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
     Corp
    -0.07
     Sour
    -0.06
     vigilant
    -0.06
    PMENT
    -0.06
    /ap
    -0.06
    ra
    -0.06
     tablets
    -0.06
    _DBG
    -0.06
     Wikipedia
    -0.06
    ası
    -0.06
    POSITIVE LOGITS
    friends
    0.08
    %%%%%%%%%%%%%%%%
    0.06
    ocyte
    0.06
    TRANS
    0.06
     fueled
    0.06
    _staff
    0.06
     enf
    0.06
    back
    0.06
     myst
    0.06
    َج
    0.06
    Activations Density 0.062%

    No Known Activations