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. 84802
    Prev
    Next
    INDEX
    Explanations

    bl

    np_max-act · gemini-2.0-flash

    This neuron selectively detects floating-point numeric values (decimal numbers) 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
    .cgColor
    -0.07
    학년도
    -0.06
    222
    -0.06
     gratuito
    -0.06
     don
    -0.06
     messing
    -0.06
     Electronics
    -0.06
    _fx
    -0.06
     lig
    -0.06
     khi
    -0.06
    POSITIVE LOGITS
    roman
    0.07
    Layout
    0.07
    キング
    0.07
      ↵
    0.07
     Folk
    0.07
    _RD
    0.06
    "=>"
    0.06
     GetString
    0.06
    	r
    0.06
    .XtraReports
    0.06
    Activations Density 0.051%

    No Known Activations