© 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. 126291
    Prev
    Next
    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric tokens (floating‐point numbers) in the text.

    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
     aç
    -0.06
     Alam
    -0.06
    Away
    -0.06
    ामन
    -0.06
    .intro
    -0.06
     SCR
    -0.06
    PERTY
    -0.06
     Numero
    -0.05
    成為
    -0.05
    ैश
    -0.05
    POSITIVE LOGITS
    &e
    0.08
    pd
    0.07
     рев
    0.07
    .setBounds
    0.07
    /************************************************************************************************
    0.06
    /************************
    0.06
     autob
    0.06
    开发
    0.06
     Hermes
    0.06
     Aberdeen
    0.06
    Activations Density 0.001%

    No Known Activations