© 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. 75413
    Prev
    Next
    INDEX
    Explanations

    references to articles or downloads

    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
    isoft
    -0.06
    ames
    -0.06
    abcdefgh
    -0.06
    apg
    -0.06
    acomment
    -0.05
    apr
    -0.05
    æīį
    -0.05
    afe
    -0.05
    stem
    -0.05
    ongyang
    -0.05
    POSITIVE LOGITS
    ISS
    0.07
     Jude
    0.07
    idd
    0.07
    RI
    0.07
    rij
    0.07
    ungs
    0.06
    iat
    0.06
    urve
    0.06
    landa
    0.06
    ijo
    0.06
    Activations Density 0.000%

    No Known Activations