© 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. 11-RESID-POST-AA
    11. 58272
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash

    code snippets or technical descriptions related to programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is specialized to detect numeric tokens, especially decimal numbers and version‐style numerals.

    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
    CMP
    -0.08
    elter
    -0.07
     Gemini
    -0.07
     Amanda
    -0.06
     frustr
    -0.06
    按照
    -0.06
     hiển
    -0.06
    Tai
    -0.06
     đầu
    -0.06
     fracking
    -0.06
    POSITIVE LOGITS
     располож
    0.07
     accelerator
    0.07
    &p
    0.07
     работ
    0.06
     }}/
    0.06
    })
    0.06
    -hooks
    0.06
    .toJson
    0.06
    =t
    0.06
    _EDGE
    0.06
    Activations Density 0.054%

    No Known Activations