© 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. 9-LLAMASCOPE-RES-131K
    11. 98640
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements presented in the text

    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
    elter
    -0.06
    CA
    -0.06
     Emb
    -0.05
     Mis
    -0.05
    492
    -0.05
    -0.05
     xo
    -0.05
    FA
    -0.05
    oa
    -0.05
     Kraj
    -0.05
    POSITIVE LOGITS
    γοÏį
    0.08
    ëŀį
    0.07
    иÑģлов
    0.07
    Cors
    0.07
    ëĿ¼ìĿ¸
    0.07
    ãĥ¼ãĥĹ
    0.07
    InMillis
    0.07
    اسÙĩ
    0.07
    _saida
    0.07
     rel
    0.07
    Activations Density 0.001%

    No Known Activations