© 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. 57983
    Prev
    Next
    INDEX
    Explanations

    terms related to business strategy and planning

    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
    erman
    -0.08
     ÑģÑĥÑĤ
    -0.07
    alten
    -0.07
    meal
    -0.07
    سÙĪب
    -0.07
    uchar
    -0.07
    że
    -0.07
    sure
    -0.07
    cmp
    -0.07
    -thirds
    -0.07
    POSITIVE LOGITS
    ically
    0.09
    ../../../
    0.08
    çķ¥
    0.08
    tical
    0.07
    -str
    0.07
    tero
    0.07
    ical
    0.07
    andle
    0.06
     lượng
    0.06
    anges
    0.06
    Activations Density 0.018%

    No Known Activations