© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13457
    Prev
    Next
    INDEX
    Explanations

    programming operators

    np_max-act · gemini-2.0-flash

    The neuron fires on quoted string keys in array or object literal definitions (i.e. the left‐hand side of a “key => value” entry).

    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
    aç
    -0.07
    -u
    -0.07
     Peninsula
    -0.06
     çiz
    -0.06
     glu
    -0.06
    .LAZY
    -0.06
     ipad
    -0.06
     himself
    -0.06
    ５
    -0.06
     регуляр
    -0.06
    POSITIVE LOGITS
     courses
    0.07
    (Order
    0.06
     incidents
    0.06
     підстав
    0.06
    ução
    0.06
    .Process
    0.06
     provid
    0.06
    (Job
    0.06
     drafting
    0.06
    بي
    0.06
    Activations Density 0.032%

    No Known Activations