© 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. 15-LLAMASCOPE-RES-131K
    11. 104173
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or appreciation

    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
    er
    -0.06
    ester
    -0.06
     Doch
    -0.06
     Gors
    -0.05
    PRS
    -0.05
    terra
    -0.05
    burger
    -0.05
    last
    -0.05
    ::_
    -0.05
     freak
    -0.05
    POSITIVE LOGITS
    chwitz
    0.09
    PFN
    0.08
    ëĿ
    0.07
    olit
    0.07
    lili
    0.07
    nonnull
    0.07
    ADIUS
    0.07
    UPER
    0.07
    adius
    0.07
     grátis
    0.07
    Activations Density 0.008%

    No Known Activations