© 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. 30628
    Prev
    Next
    INDEX
    Explanations

    structure or elements typical of code or data definitions

    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
    jie
    -0.07
    akte
    -0.06
    owie
    -0.06
    ĶåĽŀ
    -0.06
    isay
    -0.06
    ilestone
    -0.06
    unas
    -0.06
    éry
    -0.06
    zyst
    -0.06
    à¸Ĺย
    -0.06
    POSITIVE LOGITS
    #ae
    0.07
    cha
    0.07
    ë¹Ļ
    0.07
    ae
    0.06
    .Sprintf
    0.06
    igne
    0.06
    !!,
    0.06
    ISTS
    0.06
    aban
    0.06
    ,↵
    0.06
    Activations Density 0.033%

    No Known Activations