© 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. 15-LLAMASCOPE-RES-131K
    11. 87260
    Prev
    Next
    INDEX
    Explanations

    references to academic titles and professional roles

    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
    lej
    -0.08
    ÑĥÑī
    -0.08
    uly
    -0.07
    ogan
    -0.07
    eland
    -0.07
    aldi
    -0.07
    our
    -0.07
     peÄį
    -0.07
    usan
    -0.07
    ctors
    -0.07
    POSITIVE LOGITS
     cr
    0.08
    verse
    0.06
     Emer
    0.06
    [^
    0.05
     ore
    0.05
    hip
    0.05
    oon
    0.05
     åij
    0.05
    Bool
    0.05
    arta
    0.05
    Activations Density 0.007%

    No Known Activations