© 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. 69186
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    mentions of evaluation, assessment, or desirable properties (words about quality, scalability, potential, integration, and other benchmarking/criteria).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    &apos
    -0.07
     Mand
    -0.07
    mh
    -0.07
     Pok
    -0.07
     Phong
    -0.07
     dic
    -0.06
    Pok
    -0.06
     пас
    -0.06
    lings
    -0.06
     Petro
    -0.06
    POSITIVE LOGITS
    setLabel
    0.07
     ('$
    0.06
    _tip
    0.06
    ğinin
    0.06
     이러한
    0.06
     فایل
    0.06
    Verbose
    0.06
    @ResponseBody
    0.06
    =======
    0.06
    usc
    0.06
    Activations Density 0.589%

    No Known Activations