© 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. 89074
    Prev
    Next
    INDEX
    Explanations

    colon symbol

    np_max-act · gemini-2.0-flash

    This neuron detects section headings or outline-style labels (e.g., “Introduction:”, “Definition of…”, “Conclusion:”) in a structured 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
     yum
    -0.07
    '}
    -0.07
    -0.07
    idor
    -0.07
     NOR
    -0.07
    jq
    -0.07
    Smith
    -0.07
    ()"
    -0.07
     Zub
    -0.07
    TOR
    -0.06
    POSITIVE LOGITS
     :↵
    0.11
    :↵
    0.11
    :↵↵
    0.09
    ]:
↵
    0.09
    :#
    0.08
    :]:↵
    0.08
    ()):↵
    0.08
    ":
↵
    0.08
    :
↵
    0.08
    :@
    0.08
    Activations Density 0.087%

    No Known Activations