© 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. 128275
    Prev
    Next
    INDEX
    Explanations

    references to software versioning and documentation changes

    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
    arth
    -0.08
    EGIN
    -0.07
     weather
    -0.06
    weather
    -0.06
    (Clone
    -0.06
     Baz
    -0.06
    EDA
    -0.06
     Berm
    -0.06
     bowed
    -0.06
    apollo
    -0.06
    POSITIVE LOGITS
     latest
    0.07
    latest
    0.07
     správ
    0.07
    aille
    0.07
    /latest
    0.07
    ulti
    0.07
    jon
    0.06
    TouchUpInside
    0.06
    otel
    0.06
    ety
    0.06
    Activations Density 0.004%

    No Known Activations