© 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. 17-LLAMASCOPE-RES-131K
    11. 87631
    Prev
    Next
    INDEX
    Explanations

    terms related to approximations in mathematical contexts

    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
    ways
    -0.08
    uci
    -0.07
    lap
    -0.07
    lá
    -0.07
    upt
    -0.07
    eger
    -0.07
    light
    -0.06
    ear
    -0.06
    lac
    -0.06
    resi
    -0.06
    POSITIVE LOGITS
    ç¿°
    0.09
    imations
    0.08
    imate
    0.08
    ately
    0.08
    imating
    0.08
    itude
    0.08
    ingly
    0.07
    able
    0.07
    çijŁ
    0.07
    imated
    0.07
    Activations Density 0.028%

    No Known Activations