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. 127026
    Prev
    Next
    INDEX
    Explanations

    programming/technical text

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric literals, especially floating‐point numbers.

    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
    .utc
    -0.06
    Transpose
    -0.06
    tooltip
    -0.06
    sr
    -0.06
    /weather
    -0.06
    ål
    -0.06
     kans
    -0.06
     Much
    -0.06
     =======
    -0.06
     WINAPI
    -0.06
    POSITIVE LOGITS
    OLL
    0.06
     склад
    0.06
     svat
    0.06
     �
    0.06
     Root
    0.06
     ongoing
    0.06
     llev
    0.06
    .getUser
    0.06
    ีเอ
    0.06
    이비
    0.06
    Activations Density 0.296%

    No Known Activations