© 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. 17299
    Prev
    Next
    INDEX
    Explanations

    elements of critique or analysis related to performance and character assessments

    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
     but
    -0.17
     nhÆ°ng
    -0.13
    but
    -0.13
    ä½Ĩ
    -0.12
     pero
    -0.11
     maar
    -0.10
     yet
    -0.10
    ä½Ĩæĺ¯
    -0.09
     но
    -0.09
     ancak
    -0.09
    POSITIVE LOGITS
     etc
    0.09
     blah
    0.08
    )((((
    0.07
    etc
    0.07
    ãģªãģ©
    0.06
     Nor
    0.06
     ÑĤоÑīо
    0.06
     nor
    0.06
     camps
    0.06
     */,↵
    0.06
    Activations Density 0.048%

    No Known Activations