© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags descriptive character‐trait adjectives in profile or narrative 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
     سید
    -0.07
     SV
    -0.06
    actors
    -0.06
    oplan
    -0.06
     何
    -0.06
    ованих
    -0.06
    Administr
    -0.06
     batting
    -0.06
     paused
    -0.06
    尚
    -0.06
    POSITIVE LOGITS
     cann
    0.07
     constitution
    0.07
     taps
    0.06
     viet
    0.06
     århus
    0.06
     colony
    0.06
    Docs
    0.06
    ي
    0.06
     Phát
    0.06
     erste
    0.06
    Activations Density 0.007%

    No Known Activations