© 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. 81298
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and formatting in the text

    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
    rael
    -0.07
     Instrument
    -0.07
    ekil
    -0.07
    ?page
    -0.06
     fi
    -0.06
    å²³
    -0.06
    oor
    -0.06
    InstanceOf
    -0.06
    791
    -0.06
    inus
    -0.06
    POSITIVE LOGITS
    quist
    0.07
    cci
    0.06
    alink
    0.06
    INDER
    0.06
    ampion
    0.06
    uge
    0.06
    vailability
    0.06
    ovit
    0.06
    ilty
    0.06
    nicos
    0.06
    Activations Density 0.001%

    No Known Activations