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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 109106
    Prev
    Next
    INDEX
    Explanations

    code or configuration excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects code-like and technical/documentation tokens—programming identifiers, type/version strings, and structured code or schema fragments.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     δυ
    -0.06
    ]-->↵
    -0.06
    	cb
    -0.06
    ))),↵
    -0.06
    )));↵
    -0.06
     квад
    -0.06
     baj
    -0.05
    ]:=
    -0.05
    ))).
    -0.05
    .ForeColor
    -0.05
    POSITIVE LOGITS
    머
    0.07
    нен
    0.07
    없
    0.07
    ijkstra
    0.07
    emoth
    0.07
    VERSION
    0.07
     Да
    0.07
     Appears
    0.07
     răng
    0.07
    AREST
    0.07
    Activations Density 19.774%

    No Known Activations