© 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. 128290
    Prev
    Next
    INDEX
    Explanations

    scientific classifications and distribution information related to species

    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
     thresh
    -0.07
    assin
    -0.07
    amarin
    -0.07
    _reordered
    -0.06
    ιά
    -0.06
     incest
    -0.06
    ÑĢаж
    -0.06
    ầy
    -0.06
    askell
    -0.06
    .uc
    -0.06
    POSITIVE LOGITS
    onaut
    0.07
    گز
    0.06
    erdale
    0.06
    oz
    0.06
    à¹Īà¸ĩà¸Ĥ
    0.06
     mens
    0.06
    xor
    0.06
    orph
    0.06
    COMMENT
    0.06
    ensely
    0.06
    Activations Density 0.013%

    No Known Activations