© 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. 125957
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron detects section‐number markers (e.g. “#s2” or other numbered headings) in the document.

    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
     Heller
    -0.07
     byl
    -0.07
    ricao
    -0.07
    >About
    -0.07
    (/^\
    -0.07
     드립니다
    -0.06
     хоча
    -0.06
    ("\\
    -0.06
    uator
    -0.06
    екси
    -0.06
    POSITIVE LOGITS
    :<
    0.06
     변경
    0.06
     ngang
    0.06
    Software
    0.06
    IM
    0.06
     Michael
    0.06
     言
    0.06
    ARGIN
    0.06
     localtime
    0.06
    96
    0.06
    Activations Density 0.002%

    No Known Activations