Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130538
    Prev
    Next
    INDEX
    Explanations

    Code/errors

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing a decimal point.

    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
    .Dialog
    -0.07
    ηγ
    -0.07
     Achievement
    -0.06
     Chad
    -0.06
    .linear
    -0.06
     Dy
    -0.06
     자동
    -0.06
    _skip
    -0.06
     requirements
    -0.06
    Добав
    -0.06
    POSITIVE LOGITS
    cff
    0.06
    炸
    0.06
    cpp
    0.06
     engraved
    0.06
     impactful
    0.06
    ensch
    0.06
    ecut
    0.06
    ुं
    0.06
    代
    0.06
    licting
    0.06
    Activations Density 0.868%

    No Known Activations