© 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. 7990
    Prev
    Next
    INDEX
    Explanations

    fruit

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the split tokens “Ada” + “fruit,” i.e. references to the Adafruit library in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets related to Arduino programming and its components.

    oai_token-act-pair · gpt-4o-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
    Polit
    -0.08
    devil
    -0.07
     انر
    -0.07
     Barbie
    -0.07
     ********************************************************
    -0.06
     звер
    -0.06
     meg
    -0.06
     Terrain
    -0.06
     Télé
    -0.06
    Tour
    -0.06
    POSITIVE LOGITS
    ('.');↵
    0.06
     checking
    0.06
    圍
    0.06
    diff
    0.06
     dva
    0.06
     &↵
    0.06
    [first
    0.06
    ních
    0.06
    시에
    0.06
    _children
    0.06
    Activations Density 0.001%

    No Known Activations