Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80856
    Prev
    Next
    INDEX
    Explanations

    async

    np_max-act · gemini-2.0-flash

    issues related to asynchronous data fetching and promises in code.

    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
     PSD
    -0.07
    (guid
    -0.06
    methods
    -0.06
    Px
    -0.06
     gir
    -0.06
     Glasgow
    -0.06
    Detection
    -0.06
    Mus
    -0.06
     fileName
    -0.06
    ではない
    -0.06
    POSITIVE LOGITS
    /sql
    0.06
     конферен
    0.06
    ,ll
    0.06
     QS
    0.06
     zru
    0.06
     */
    ↵
    ↵
    0.06
     casualty
    0.06
     Ancak
    0.06
     доктор
    0.06
    uth
    0.06
    Activations Density 0.004%

    No Known Activations