© 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. 61681
    Prev
    Next
    INDEX
    Explanations

    terms related to inspections 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
     addCriterion
    -0.08
    UnderTest
    -0.08
     {{--<
    -0.07
    _SCHED
    -0.07
    ẹn
    -0.07
    hiba
    -0.06
    éļĽ
    -0.06
    esel
    -0.06
    ovel
    -0.06
    tru
    -0.06
    POSITIVE LOGITS
     conducted
    0.13
     performed
    0.12
     done
    0.10
     Conduct
    0.10
     carried
    0.09
     completed
    0.08
    done
    0.08
     conduct
    0.07
    completed
    0.07
     пÑĢовод
    0.07
    Activations Density 0.043%

    No Known Activations