© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92099
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    This neuron fires on the very first token of each listed or captioned item—i.e. it spotlights the word that begins a new caption, table row, or bullet-style entry.

    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
    ass
    -0.07
    ASS
    -0.07
     calcium
    -0.06
     ngày
    -0.06
     podium
    -0.06
    IALOG
    -0.06
    ованих
    -0.06
    /master
    -0.06
    _qs
    -0.06
    (Attribute
    -0.06
    POSITIVE LOGITS
     Fund
    0.07
    .trim
    0.07
     discriminatory
    0.06
    ){//
    0.06
    _CheckedChanged
    0.06
     "}\
    0.06
     BrowserRouter
    0.06
     =>'
    0.06
    los
    0.06
    ling
    0.06
    Activations Density 0.049%

    No Known Activations