© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82542
    Prev
    Next
    INDEX
    Explanations

    discussions about coding efficiency and simplicity

    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
    Wunused
    -0.07
    fony
    -0.07
    ichick
    -0.07
    ensed
    -0.07
    _override
    -0.07
    ãĥ³ãĥIJ
    -0.06
    -addons
    -0.06
    ersiz
    -0.06
     ÙģرÙĪد
    -0.06
    ÑĤож
    -0.06
    POSITIVE LOGITS
    ered
    0.07
    quez
    0.06
    ube
    0.06
    Perl
    0.06
     LIN
    0.06
    208
    0.06
    Submitted
    0.06
    UTIL
    0.05
     uncert
    0.05
    057
    0.05
    Activations Density 0.019%

    No Known Activations