© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 119612
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high performance and quality in engineering or product descriptions

    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
    enburg
    -0.07
     (
    -0.06
    igo
    -0.06
     doomed
    -0.06
    postalcode
    -0.06
    246
    -0.06
    YO
    -0.06
    LOSS
    -0.05
     whose
    -0.05
    /L
    -0.05
    POSITIVE LOGITS
     performance
    0.08
    icari
    0.07
    unker
    0.07
    ablish
    0.07
    énom
    0.07
    ayi
    0.07
    .Apis
    0.07
     economics
    0.07
     overall
    0.07
     performances
    0.07
    Activations Density 0.019%

    No Known Activations