© 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. 62142
    Prev
    Next
    INDEX
    Explanations

    words related to acceleration and programs designed to enhance learning or innovation

    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
    amba
    -0.09
    soever
    -0.07
    mul
    -0.07
    fulness
    -0.07
    ega
    -0.07
    azon
    -0.07
    uelle
    -0.07
    ality
    -0.07
    iculty
    -0.07
    adle
    -0.07
    POSITIVE LOGITS
    boa
    0.07
    bris
    0.07
    otti
    0.07
    ator
    0.07
    ena
    0.06
    aby
    0.06
    ators
    0.06
    onian
    0.06
    /de
    0.06
    åĻ¨
    0.06
    Activations Density 0.022%

    No Known Activations