© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103991
    Prev
    Next
    INDEX
    Explanations

    terms related to achieving success and reaching goals

    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
    fy
    -0.06
    erton
    -0.06
    èªĮ
    -0.06
    ¯
    -0.06
    acht
    -0.06
    ipel
    -0.06
    illo
    -0.06
    ied
    -0.06
    rott
    -0.06
     Mezi
    -0.06
    POSITIVE LOGITS
    contri
    0.07
     basit
    0.07
    DEFINED
    0.07
     omas
    0.07
     —↵↵
    0.07
     Erk
    0.07
    /win
    0.06
    ROTO
    0.06
    리ëĬĶ
    0.06
    InParameter
    0.06
    Activations Density 0.013%

    No Known Activations