© 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. 86588
    Prev
    Next
    INDEX
    Explanations

    names of authors and affiliations related to academic research

    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
    utto
    -0.07
    olo
    -0.06
    este
    -0.06
    izio
    -0.06
    ↵
    -0.06
    uong
    -0.06
    -
    -0.06
    -and
    -0.06
    CHIP
    -0.06
    üss
    -0.06
    POSITIVE LOGITS
    allen
    0.09
     Lv
    0.08
     Hait
    0.08
    .Ma
    0.08
    cheng
    0.08
    lili
    0.08
    ]={↵
    0.08
    aoke
    0.08
    lei
    0.08
     X
    0.08
    Activations Density 0.091%

    No Known Activations