© 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. 42629
    Prev
    Next
    INDEX
    Explanations

    Experiences and themes

    np_max-act · gemini-2.0-flash

    This neuron fires on the labeled theme or category headings (e.g. “practical and emotional challenges,” “program‐related barriers,” “family support,” etc.) that structure qualitative study findings.

    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
    х
    -0.07
    áct
    -0.07
    CppMethodIntialized
    -0.06
    	code
    -0.06
    حی
    -0.06
     Paw
    -0.06
    계획
    -0.06
     clinicians
    -0.06
    acomment
    -0.06
    _space
    -0.06
    POSITIVE LOGITS
    물을
    0.07
    _fill
    0.07
    ?action
    0.06
    (theme
    0.06
    .dup
    0.06
    &page
    0.06
    .DOM
    0.06
    (axis
    0.06
     وغير
    0.06
    �
    0.06
    Activations Density 0.047%

    No Known Activations