© 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. 76118
    Prev
    Next
    INDEX
    Explanations

    terms related to recommendations and assessments in various contexts

    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
    ovich
    -0.08
    istor
    -0.07
    ozem
    -0.07
    gle
    -0.07
    пÑĢиклад
    -0.07
    λη
    -0.06
    aro
    -0.06
    classed
    -0.06
    WISE
    -0.06
    à¥įतर
    -0.06
    POSITIVE LOGITS
     vs
    0.11
     versus
    0.10
    argon
    0.08
    ness
    0.08
    -vs
    0.08
     ness
    0.08
    _vs
    0.08
     areas
    0.08
     Vs
    0.07
    rees
    0.07
    Activations Density 0.063%

    No Known Activations