© 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. 44151
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron primarily detects numeric tokens, especially decimal 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
    ataset
    -0.07
     Coin
    -0.07
     Leia
    -0.06
     Efficient
    -0.06
     É
    -0.06
     mocker
    -0.06
    ogenerated
    -0.06
    .show
    -0.06
    Day
    -0.06
     KAR
    -0.06
    POSITIVE LOGITS
     catastrophe
    0.07
     abandon
    0.06
    ۱۹۴
    0.06
     thro
    0.06
    plete
    0.06
     buna
    0.06
     �
    0.06
     oto
    0.06
    asad
    0.06
    vou
    0.06
    Activations Density 0.001%

    No Known Activations