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. 84932
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing signed decimal (floating‐point) values.

    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
     awake
    -0.06
     Suppliers
    -0.06
     Engineer
    -0.06
    Input
    -0.06
    umped
    -0.06
     Wik
    -0.06
     ده
    -0.06
    	uint
    -0.06
    SizePolicy
    -0.05
     myš
    -0.05
    POSITIVE LOGITS
    "}
    0.07
     overlooked
    0.06
    ————————
    0.06
    170
    0.06
    ,而且
    0.06
    )animated
    0.06
     judgment
    0.06
    岗位
    0.06
    ้า
    0.06
     exhausted
    0.06
    Activations Density 0.006%

    No Known Activations