© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92195
    Prev
    Next
    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash

    This neuron spots numeric values associated with sentencing guideline calculations (e.g. guideline ranges and enhancement levels).

    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
     sewing
    -0.07
    Formation
    -0.06
     Leben
    -0.06
    γι
    -0.06
     ウ
    -0.06
     Unternehmen
    -0.06
    Carousel
    -0.06
     maint
    -0.06
    -split
    -0.06
     Symphony
    -0.06
    POSITIVE LOGITS
    氧
    0.07
     Terraria
    0.06
    .global
    0.06
     için
    0.06
    álně
    0.06
    òa
    0.06
     blurry
    0.06
    antage
    0.06
     irgend
    0.06
    jure
    0.06
    Activations Density 0.002%

    No Known Activations