© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125956
    Prev
    Next
    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash

    The neuron detects underscore tokens (e.g. the “_” in autogenerated Javadoc version strings).

    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
    youtube
    -0.06
     pager
    -0.06
    зации
    -0.06
    ---
↵
    -0.06
     Neural
    -0.06
     Caul
    -0.06
    وی
    -0.06
     offsetX
    -0.06
     Giles
    -0.06
    =center
    -0.06
    POSITIVE LOGITS
     �
    0.07
     condemned
    0.07
     pkg
    0.07
    .getNext
    0.06
     которой
    0.06
    igaret
    0.06
    spor
    0.06
     '/'↵
    0.06
    .setError
    0.06
    .inf
    0.06
    Activations Density 0.001%

    No Known Activations