© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125223
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical identifiers or citations

    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
    veau
    -0.08
    itary
    -0.07
    anning
    -0.07
    rol
    -0.07
    lv
    -0.06
    omid
    -0.06
    erb
    -0.06
    yor
    -0.06
     Loren
    -0.06
    phy
    -0.06
    POSITIVE LOGITS
    etadata
    0.08
    .mybatisplus
    0.08
    itect
    0.07
    FileType
    0.07
    eton
    0.07
    ENTS
    0.07
    ĸ
    0.07
    rire
    0.07
    ÙĨدÛĮ
    0.07
    ERCHANT
    0.07
    Activations Density 0.012%

    No Known Activations