© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88707
    Prev
    Next
    INDEX
    Explanations

    terms related to iterative processes or algorithms

    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
    ses
    -0.08
    heit
    -0.08
    oji
    -0.08
    edException
    -0.08
    sess
    -0.08
    verity
    -0.08
    owler
    -0.07
    agini
    -0.07
    eur
    -0.07
    sid
    -0.07
    POSITIVE LOGITS
    ative
    0.09
    ally
    0.08
    atively
    0.08
    istically
    0.07
    éª
    0.07
    rex
    0.07
    à¸Ļ
    0.07
    imestep
    0.07
    inary
    0.06
    oman
    0.06
    Activations Density 0.013%

    No Known Activations