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. 130304
    Prev
    Next
    INDEX
    Explanations

    ds

    np_max-act · gemini-2.0-flash

    This neuron specifically picks up on numerical statistical effect‐size values (e.g. odds ratios) 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
    ヘ
    -0.08
    Lab
    -0.07
     StreamWriter
    -0.06
     Albert
    -0.06
    clone
    -0.06
    ربی
    -0.06
     Але
    -0.06
     Christian
    -0.06
    ستان
    -0.06
     failed
    -0.06
    POSITIVE LOGITS
     odds
    0.07
     elic
    0.06
    omens
    0.06
     rau
    0.06
     targeting
    0.06
    -night
    0.06
     fancy
    0.06
    plet
    0.06
    Byte
    0.06
    ordo
    0.06
    Activations Density 0.004%

    No Known Activations