© 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. 117905
    Prev
    Next
    INDEX
    Explanations

    references to gaming missions and elements related to gameplay mechanics

    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
    ricks
    -0.08
    attles
    -0.07
    byss
    -0.07
    Å¡i
    -0.07
    lah
    -0.07
    opard
    -0.07
    ulace
    -0.07
    AUTH
    -0.06
    891
    -0.06
    rescia
    -0.06
    POSITIVE LOGITS
    lvl
    0.07
    obl
    0.06
    traction
    0.06
    alis
    0.06
     pole
    0.06
     Folk
    0.06
    #endregion
    0.06
    apas
    0.06
     Arts
    0.06
    åªĴ
    0.06
    Activations Density 0.025%

    No Known Activations