© 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. 22-LLAMASCOPE-RES-131K
    11. 3914
    Prev
    Next
    INDEX
    Explanations

    references to context and perspectives in discussions

    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
    iali
    -0.06
    oki
    -0.06
    fe
    -0.06
    opa
    -0.06
    ilim
    -0.06
    hiro
    -0.06
    ibir
    -0.05
    eton
    -0.05
    isay
    -0.05
    87
    -0.05
    POSITIVE LOGITS
    duino
    0.07
    viso
    0.07
    تÙĬÙĨ
    0.07
    oard
    0.07
    ãĤ¿ãĥ³
    0.07
    roller
    0.07
    .Expressions
    0.07
    ries
    0.07
     ofrec
    0.07
    TypeInfo
    0.07
    Activations Density 0.019%

    No Known Activations