© 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. 94327
    Prev
    Next
    INDEX
    Explanations

    terms related to selection and assessment processes in a competitive environment

    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
    ioso
    -0.07
    _least
    -0.07
    ковод
    -0.07
    ÑĨин
    -0.07
    OptionsMenu
    -0.07
     èµ·
    -0.06
    elp
    -0.06
    ойно
    -0.06
    throp
    -0.06
    ripp
    -0.06
    POSITIVE LOGITS
     discretion
    0.09
     determined
    0.08
     determination
    0.08
    erner
    0.08
     decide
    0.07
     decision
    0.07
     may
    0.07
     determine
    0.07
     reasons
    0.07
     determining
    0.07
    Activations Density 0.016%

    No Known Activations