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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 108764
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens — tokens containing digits or numeric values (numbers, numeric identifiers, or numeric-like substrings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rail
    -0.07
    _api
    -0.07
     заболева
    -0.07
     беременности
    -0.07
    enuous
    -0.06
     Primitive
    -0.06
     разм
    -0.06
    ################################################################
    -0.06
    (qu
    -0.06
    (ne
    -0.06
    POSITIVE LOGITS
     SPE
    0.06
     Baker
    0.06
     gif
    0.06
     Bryant
    0.06
     investing
    0.06
     petitions
    0.06
     çeşit
    0.06
    impan
    0.06
     Panther
    0.06
    bull
    0.06
    Activations Density 0.001%

    No Known Activations