© 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. 7875
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron fires on meta‐discourse and evaluative commentary markers—words like “detail,” “reason,” “tends,” “frown,” and “on” that signal the author’s commentary or judgment.

    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
    .addValue
    -0.07
     المك
    -0.07
     ↔
    -0.07
    -CS
    -0.07
    อลลาร
    -0.07
    _MED
    -0.06
    ,以
    -0.06
     TableColumn
    -0.06
    academic
    -0.06
    UNG
    -0.06
    POSITIVE LOGITS
     çıkar
    0.06
    (inputStream
    0.06
    orgh
    0.06
    벨
    0.06
     jedn
    0.06
    ("");↵
    0.06
     trains
    0.06
     분
    0.06
     sh
    0.06
    ixture
    0.06
    Activations Density 0.097%

    No Known Activations