© 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. 15-LLAMASCOPE-RES-131K
    11. 104103
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding technological challenges and solutions

    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
    ã
    -0.07
    zm
    -0.07
    Traversal
    -0.06
    elta
    -0.06
    æ³¥
    -0.06
     Sadd
    -0.06
    egree
    -0.06
    loor
    -0.06
    MatrixMode
    -0.06
    ána
    -0.06
    POSITIVE LOGITS
     succeeds
    0.07
     succeed
    0.07
     DÃŃky
    0.07
     succeeded
    0.06
    otope
    0.06
    kins
    0.06
    usi
    0.06
     Tento
    0.06
    ynos
    0.06
     successful
    0.06
    Activations Density 0.113%

    No Known Activations