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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126483
    Prev
    Next
    INDEX
    Explanations

    references to collective experiences or community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugins
    -0.07
    ardin
    -0.07
    .HtmlControls
    -0.07
    ities
    -0.07
    ưá»Ŀi
    -0.06
    felt
    -0.06
    ellan
    -0.06
    untime
    -0.06
    geist
    -0.06
    undy
    -0.06
    POSITIVE LOGITS
    kker
    0.06
     tolua
    0.06
    reader
    0.06
    atham
    0.06
    -shift
    0.06
    ifikasi
    0.06
    tek
    0.06
    ëĵľë¡ľ
    0.06
    ì͍
    0.06
     lesson
    0.06
    Activations Density 0.018%

    No Known Activations