© 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. 5-LLAMASCOPE-RES-131K
    11. 126841
    Prev
    Next
    INDEX
    Explanations

    instances of the word "further."

    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
    orm
    -0.07
    OMIC
    -0.06
    stm
    -0.06
    lein
    -0.06
    run
    -0.06
    uv
    -0.06
    emu
    -0.06
    ellular
    -0.06
    aku
    -0.06
    بÙĨ
    -0.06
    POSITIVE LOGITS
    -than
    0.07
     rounds
    0.07
     than
    0.07
    mland
    0.07
    iferay
    0.07
    anging
    0.07
    ozor
    0.06
    _than
    0.06
     Rounds
    0.06
    iversit
    0.06
    Activations Density 0.008%

    No Known Activations