© 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. 25333
    Prev
    Next
    INDEX
    Explanations

    questions and quotes

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on special control tokens that mark the end of a message or turn (e.g. the “<|eot_id|>” end‐of‐turn marker).

    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
     hopefully
    -0.07
    賢
    -0.07
     ultimately
    -0.07
     fortunately
    -0.07
     unfortunately
    -0.06
    anders
    -0.06
     nonetheless
    -0.06
     ]),↵
    -0.06
     disappointed
    -0.06
    charged
    -0.06
    POSITIVE LOGITS
     yeme
    0.08
    /Instruction
    0.07
     Veronica
    0.06
     HBO
    0.06
     Vegas
    0.06
    (getContext
    0.06
    πή
    0.06
     Rencontre
    0.06
     AUTH
    0.06
     lå
    0.06
    Activations Density 0.061%

    No Known Activations