© 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. 17-LLAMASCOPE-RES-131K
    6. 29597
    Prev
    Next
    INDEX
    Explanations

    terms related to adequacy and sufficiency, especially in the context of resources or conditions

    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
    neau
    -0.08
    foundland
    -0.08
    sdale
    -0.07
    so
    -0.07
    alogy
    -0.07
    bing
    -0.07
    thic
    -0.07
    تÙĬÙĨ
    -0.06
    writing
    -0.06
    side
    -0.06
    POSITIVE LOGITS
    -sized
    0.09
    quate
    0.09
     sized
    0.08
    ately
    0.08
     amount
    0.08
    ÑģÑĮ
    0.07
    ably
    0.07
    )prepare
    0.07
     Sized
    0.07
    utom
    0.07
    Activations Density 0.006%

    No Known Activations