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. 129358
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals written with decimal points (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
    ressed
    -0.06
     coded
    -0.06
    Begin
    -0.06
     Ally
    -0.06
    Decoder
    -0.06
     families
    -0.06
    cpu
    -0.06
    .fore
    -0.06
     encounter
    -0.06
    领导
    -0.06
    POSITIVE LOGITS
    >';
    0.07
    金融
    0.07
    <span
    0.07
     začal
    0.06
     els
    0.06
    _DET
    0.06
     unspecified
    0.06
    _CHANGE
    0.06
     řekl
    0.06
     ---------
    0.06
    Activations Density 0.003%

    No Known Activations