© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8999
    Prev
    Next
    INDEX
    Explanations

    Parts of larger texts

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens—especially digits or year–like strings—and the words immediately around them.

    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
    Fair
    -0.06
     PUS
    -0.06
     penetrating
    -0.06
     معروف
    -0.06
    prog
    -0.06
     gruesome
    -0.06
    иб
    -0.06
     cvs
    -0.06
    時の
    -0.06
     Problems
    -0.06
    POSITIVE LOGITS
    awai
    0.08
    _lista
    0.07
    }')↵
    0.07
     Celebrity
    0.06
     ncols
    0.06
     είχε
    0.06
     classroom
    0.06
    _IP
    0.06
    スタ
    0.06
    aginator
    0.06
    Activations Density 0.002%

    No Known Activations