© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128757
    Prev
    Next
    INDEX
    Explanations

    not in use

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric tokens representing decimal fractions (i.e. the “0.xxx” parts of float 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
    words
    -0.07
    С
    -0.06
     branding
    -0.06
     получить
    -0.06
    两
    -0.06
    หลาย
    -0.06
     Drama
    -0.06
     mon
    -0.06
     compares
    -0.06
    distance
    -0.06
    POSITIVE LOGITS
    krvldkf
    0.07
    UGHT
    0.07
     amaç
    0.06
    /apis
    0.06
    τωση
    0.06
    Xã
    0.06
    Cached
    0.06
    пион
    0.06
     recyclerView
    0.06
    Mp
    0.06
    Activations Density 0.023%

    No Known Activations