© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42575
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of MAP kinase signaling components (e.g., “MAP K,” “MEK,” “ERK,” or “kinase” in that pathway).

    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
     trick
    -0.06
    Tier
    -0.06
     콘
    -0.06
    ِه
    -0.06
     Ś
    -0.06
    lero
    -0.06
     Chlor
    -0.06
    éfono
    -0.06
     dáng
    -0.06
    (dr
    -0.06
    POSITIVE LOGITS
    never
    0.07
     постоянно
    0.07
    料理
    0.07
    .getTime
    0.07
     experienced
    0.06
    泡
    0.06
     wikipedia
    0.06
    	close
    0.06
    assign
    0.06
     promoters
    0.06
    Activations Density 0.002%

    No Known Activations