© 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. 70616
    Prev
    Next
    INDEX
    Explanations

    expressions of contrast or exception in statements

    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
    oot
    -0.07
    atz
    -0.07
    ider
    -0.06
     Ladies
    -0.06
     zwar
    -0.06
     Other
    -0.06
    ichen
    -0.06
     Different
    -0.06
    ÎĨ
    -0.06
    .assertNot
    -0.06
    POSITIVE LOGITS
     generally
    0.13
     common
    0.11
     always
    0.11
    always
    0.09
    -common
    0.09
    common
    0.09
     commonly
    0.09
     geral
    0.08
     overall
    0.08
     typically
    0.08
    Activations Density 0.022%

    No Known Activations