© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95683
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and institutions

    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
    öm
    -0.07
    anded
    -0.07
    ordo
    -0.07
    arna
    -0.06
    Poster
    -0.06
    ikon
    -0.06
    thouse
    -0.06
    lÃŃ
    -0.06
    urtle
    -0.06
    hest
    -0.06
    POSITIVE LOGITS
    uba
    0.06
    à¸Ĥà¸ĵะ
    0.06
    velte
    0.06
    idden
    0.06
    yi
    0.06
    å¯Ł
    0.06
    burgh
    0.06
    488
    0.06
    arez
    0.06
    idel
    0.06
    Activations Density 0.017%

    No Known Activations