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. 73406
    Prev
    Next
    INDEX
    Explanations

    changes in process/narrative

    np_max-act · gemini-2.0-flash

    This neuron specifically detects floating-point (decimal) numeric tokens in the 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
     Extremely
    -0.07
     освіт
    -0.07
    iche
    -0.06
    icro
    -0.06
     Swamp
    -0.06
     Addison
    -0.06
     Nate
    -0.06
     Bain
    -0.06
    _SIMPLE
    -0.06
     Poe
    -0.06
    POSITIVE LOGITS
     rf
    0.07
    ा,
    0.07
    >
    0.07
    ี,
    0.07
    _POSTFIELDS
    0.06
    ,P
    0.06
     Pop
    0.06
    »،
    0.06
     akka
    0.06
     Price
    0.06
    Activations Density 0.128%

    No Known Activations