© 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. 108006
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and data management

    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
    pike
    -0.07
    using
    -0.07
     Mara
    -0.07
     seins
    -0.07
    581
    -0.07
    Charset
    -0.07
     Cheap
    -0.06
    erp
    -0.06
    ç¶
    -0.06
     Bowling
    -0.06
    POSITIVE LOGITS
    ozem
    0.07
    lops
    0.07
     Scot
    0.06
    orr
    0.06
     swagger
    0.06
    lant
    0.06
    _Desc
    0.06
    accum
    0.06
     personalities
    0.06
     OE
    0.06
    Activations Density 0.030%

    No Known Activations