© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6927
    Prev
    Next
    INDEX
    Explanations

    computer science problems

    np_max-act · gemini-2.0-flash

    The neuron fires on words that signal decision or decidability (e.g. mentions of deciding, decidable, decision) in complexity‐theory questions.

    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
    Elite
    -0.07
    Logical
    -0.06
    Postal
    -0.06
    :href
    -0.06
     listar
    -0.06
    Contains
    -0.06
     덤프
    -0.06
    Typ
    -0.06
     directed
    -0.06
    emploi
    -0.06
    POSITIVE LOGITS
    萬
    0.06
    ounding
    0.06
    -ended
    0.06
    万
    0.06
    制度
    0.06
    ADX
    0.06
    _split
    0.06
    /order
    0.06
    loha
    0.06
    ッ
    0.06
    Activations Density 0.011%

    No Known Activations