© 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. 41663
    Prev
    Next
    INDEX
    Explanations

    At

    np_max-act · gemini-2.0-flash

    This neuron activates on the conjunction “At” when it begins a phrase (e.g., “At the same time,” “At any given time,” “At times,” etc.).

    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
    obox
    -0.07
    such
    -0.07
    .fn
    -0.07
    邦
    -0.07
     such
    -0.07
    كون
    -0.07
     Investments
    -0.07
     witches
    -0.07
    .Comp
    -0.06
     winnings
    -0.06
    POSITIVE LOGITS
     At
    0.15
    At
    0.13
    “At
    0.11
    "At
    0.10
     at
    0.10
    .At
    0.09
    -at
    0.09
    (@(
    0.08
    at
    0.08
     nt
    0.07
    Activations Density 0.022%

    No Known Activations