© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56860
    Prev
    Next
    INDEX
    Explanations

    evaluative terms related to quality and satisfaction

    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
     chứ
    -0.08
    indh
    -0.08
    ë²
    -0.07
    umba
    -0.07
    ilip
    -0.07
    ntax
    -0.07
    chten
    -0.07
    ož
    -0.07
    hazi
    -0.07
     both
    -0.07
    POSITIVE LOGITS
     nor
    0.23
     anymore
    0.18
    nor
    0.16
    Nor
    0.14
     Nor
    0.14
     NOR
    0.12
     either
    0.10
     necessarily
    0.09
     neither
    0.09
     EITHER
    0.09
    Activations Density 0.061%

    No Known Activations