© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 7327
    Prev
    Next
    INDEX
    Explanations

    not equal to

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literals (numbers and numeric constants) in code and technical text.

    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
    perienced
    -0.07
    ťan
    -0.07
     accuracy
    -0.07
     kak
    -0.06
    stddef
    -0.06
     ponto
    -0.06
     jedné
    -0.06
     JSONObject
    -0.06
    郑
    -0.06
     ejac
    -0.06
    POSITIVE LOGITS
    ;↵↵↵↵↵
    0.06
    iterated
    0.06
     lamin
    0.06
    larak
    0.06
    нення
    0.06
    nar
    0.06
    >↵↵↵↵↵
    0.06
    ↵
↵
↵
    0.06
     tribal
    0.06
     fetchData
    0.06
    Activations Density 0.019%

    No Known Activations