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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117166
    Prev
    Next
    INDEX
    Explanations

    references to clickable links or actions

    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
    .springboot
    -0.07
     pok
    -0.06
    IFS
    -0.06
    piel
    -0.06
    451
    -0.06
    elik
    -0.06
    igos
    -0.06
    ãĥ³ãĤº
    -0.06
     quot
    -0.06
    amos
    -0.06
    POSITIVE LOGITS
    ervas
    0.06
     Kurt
    0.06
    ÑģÑİ
    0.06
     tune
    0.06
    /block
    0.06
    WRAPPER
    0.06
    çº
    0.06
     turnout
    0.06
     effectiveness
    0.06
    /opt
    0.06
    Activations Density 0.000%

    No Known Activations