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. 61068
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific characteristics or qualities about subjects

    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
    atin
    -0.06
    ativ
    -0.06
     memor
    -0.06
    ingleton
    -0.06
    ullo
    -0.06
    latin
    -0.06
    διά
    -0.06
    bookmark
    -0.06
    empl
    -0.06
    riott
    -0.06
    POSITIVE LOGITS
    ãĤ¹ãĥĿ
    0.07
    acha
    0.06
    ê
    0.06
    lili
    0.06
    Ñĸдом
    0.06
     onBind
    0.06
    Mocks
    0.06
    layıcı
    0.06
    irsch
    0.06
    atis
    0.06
    Activations Density 0.003%

    No Known Activations