© 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. 92075
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “end” when it appears as a prefix in words (e.g. endotoxin, endotoxemia, endotherm, end‐stage).

    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
    .ser
    -0.07
     hamburger
    -0.06
    ật
    -0.06
     milfs
    -0.06
     버
    -0.06
     Motorola
    -0.06
     geographic
    -0.06
    .Scheme
    -0.06
     tisíc
    -0.06
     图
    -0.06
    POSITIVE LOGITS
     End
    0.11
     end
    0.10
     endemic
    0.08
    END
    0.08
    end
    0.08
     END
    0.07
    _DD
    0.07
    .End
    0.07
    :end
    0.07
     outcome
    0.07
    Activations Density 0.009%

    No Known Activations