© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71899
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Informational content that explains concepts, relationships or processes within educational or technical text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ::.
    -0.10
     ëĭ¤ìļ´ë°Ľê¸°
    -0.10
    voje
    -0.10
    ï¼ł
    -0.10
    ï¿¥
    -0.09
    klad
    -0.09
    #echo
    -0.09
    ÛĮÛĮÙĨ
    -0.09
    âĻ¡
    -0.09
    ÛĢ
    -0.09
    POSITIVE LOGITS
    ame
    0.06
    rowsable
    0.06
    0.05
    chap
    0.05
    --
    0.05
     ðŁ
    0.05
    0.05
     borne
    0.05
     Air
    0.05
     on
    0.05
    Activations Density 0.119%

    No Known Activations