© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15809
    Prev
    Next
    INDEX
    Explanations

    references to various challenges and problems faced by a group or community

    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
    sj
    -0.07
    aterangepicker
    -0.07
    uki
    -0.07
    uhan
    -0.07
    DMIN
    -0.07
    han
    -0.07
    udic
    -0.07
    ideographic
    -0.07
    sehen
    -0.06
    ä¼Ļ
    -0.06
    POSITIVE LOGITS
    htm
    0.06
    /all
    0.06
    fila
    0.06
     TMPro
    0.06
     hall
    0.06
     dil
    0.05
    itzer
    0.05
    FACE
    0.05
     Bord
    0.05
    BI
    0.05
    Activations Density 0.013%

    No Known Activations