© 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. 125740
    Prev
    Next
    INDEX
    Explanations

    discussions and processes involving reflection and decision-making

    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
    visor
    -0.08
     eldre
    -0.08
    kening
    -0.07
    vise
    -0.07
    ColumnsMode
    -0.07
    anske
    -0.07
    tÃŃ
    -0.07
    GLOSS
    -0.07
    unch
    -0.07
    okens
    -0.07
    POSITIVE LOGITS
     until
    0.08
     whether
    0.07
     decision
    0.07
     decided
    0.06
    æĺ¯åIJ¦
    0.06
    until
    0.06
     decides
    0.06
     quyết
    0.06
     æĺ¯åIJ¦
    0.06
     id
    0.06
    Activations Density 0.026%

    No Known Activations