Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1562
    Prev
    Next
    INDEX
    Explanations

    Acetyl-CoA metabolism

    np_max-act · gemini-2.0-flash

    The neuron is highly activated by biochemical metabolite names—especially “acetyl-CoA” and related chemical compound terms.

    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
    @\
    -0.07
    操作
    -0.06
     dahil
    -0.06
     chips
    -0.06
     grapes
    -0.06
    ides
    -0.06
     puzz
    -0.06
    ход
    -0.06
    _tokens
    -0.06
    ops
    -0.06
    POSITIVE LOGITS
    .Integer
    0.07
    Quantity
    0.07
     Muhammad
    0.06
    ;'↵
    0.06
    Mis
    0.06
    فتم
    0.06
    -custom
    0.06
    Produto
    0.06
    推
    0.06
     दब
    0.06
    Activations Density 0.013%

    No Known Activations