© 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. 56675
    Prev
    Next
    INDEX
    Explanations

    terms related to underestimation or misjudgment of value or significance

    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
    iska
    -0.08
    uzey
    -0.08
    ron
    -0.07
    antan
    -0.07
    tat
    -0.07
    ecimal
    -0.07
    rada
    -0.06
    ndl
    -0.06
    alez
    -0.06
    lier
    -0.06
    POSITIVE LOGITS
     importance
    0.09
    /null
    0.08
     Importance
    0.08
     capabilities
    0.07
    hend
    0.06
    ably
    0.06
     önem
    0.06
    ÑĥÑģ
    0.06
    .Scope
    0.06
    mlin
    0.06
    Activations Density 0.004%

    No Known Activations