© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43274
    Prev
    Next
    INDEX
    Explanations

    density

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of bone mineral density and its measurement (e.g. “bone mineral density,” BMD, and related quantitative terms).

    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
    保持
    -0.07
    生き
    -0.06
    Lot
    -0.06
    IP
    -0.06
     pickup
    -0.06
    UND
    -0.06
     Coke
    -0.06
     errs
    -0.05
    ip
    -0.05
    AVED
    -0.05
    POSITIVE LOGITS
    	priv
    0.07
    :"",
    0.07
     mainAxisAlignment
    0.07
    Solar
    0.07
     명
    0.07
     apprent
    0.07
    жно
    0.07
    ayment
    0.07
     OSX
    0.07
    mong
    0.06
    Activations Density 0.006%

    No Known Activations