© 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. 43255
    Prev
    Next
    INDEX
    Explanations

    H3K27 methylation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of histone H3 lysine-27 methylation (e.g. “H3K27me1/2/3”).

    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
    .Phone
    -0.06
    isté
    -0.06
     sánh
    -0.06
    irth
    -0.06
    female
    -0.06
    _build
    -0.06
    Coefficient
    -0.06
     fulfilled
    -0.06
     months
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
     Heb
    0.08
    /javascript
    0.07
     AWS
    0.06
    MQ
    0.06
     Olomou
    0.06
    ใบ
    0.06
     comet
    0.06
    обра�
    0.06
     імен
    0.06
     allowances
    0.06
    Activations Density 0.001%

    No Known Activations