© 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. 109825
    Prev
    Next
    INDEX
    Explanations

    cr

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words associated with crocheting (e.g. “Crocheted,” the “Boshi” brand), i.e. it’s detecting crochet/craft‐related content.

    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
    bane
    -0.07
        
↵
↵
    -0.06
    Ljava
    -0.06
     sudo
    -0.06
    +v
    -0.06
     dye
    -0.06
    '))->
    -0.06
    &display
    -0.06
     Django
    -0.06
     oblasti
    -0.06
    POSITIVE LOGITS
     phố
    0.07
    _FILENAME
    0.06
    ross
    0.06
     avons
    0.06
    .Compare
    0.06
    -facing
    0.06
     stren
    0.06
     �
    0.06
     исключ
    0.06
    坡
    0.06
    Activations Density 0.585%

    No Known Activations