© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56307
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptive physical‐appearance adjectives (e.g. hair color, eye color, complexion, softness) in character‐description text.

    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
    중에
    -0.07
    URLException
    -0.07
    ♪↵↵
    -0.06
    [:,:,
    -0.06
     벽
    -0.06
     bureaucrats
    -0.06
    чного
    -0.06
     ゙
    -0.06
    ]+\
    -0.06
     activeClassName
    -0.06
    POSITIVE LOGITS
    aj
    0.07
     curated
    0.07
     Rah
    0.07
     er
    0.07
    iliated
    0.07
     Rand
    0.06
    นค
    0.06
    States
    0.06
     Ancient
    0.06
    eded
    0.06
    Activations Density 0.047%

    No Known Activations