© 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. 105726
    Prev
    Next
    INDEX
    Explanations

    phrases related to exact matches and quotations

    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
    EDI
    -0.07
    636
    -0.06
    inen
    -0.06
    UTILITY
    -0.05
    doch
    -0.05
    onia
    -0.05
    638
    -0.05
     civilized
    -0.05
    uzzi
    -0.05
     íĸ¥
    -0.05
    POSITIVE LOGITS
     exact
    0.24
     exactly
    0.21
    exact
    0.19
    Exact
    0.19
     Exact
    0.19
    _exact
    0.17
     Exactly
    0.16
     identical
    0.15
    Exactly
    0.14
    verbatim
    0.14
    Activations Density 0.064%

    No Known Activations