© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71053
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and research advancements

    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
    wat
    -0.07
    mur
    -0.07
    acic
    -0.07
    覧
    -0.07
    ovol
    -0.06
     Wah
    -0.06
    sez
    -0.06
    wand
    -0.06
    atura
    -0.06
    ooter
    -0.06
    POSITIVE LOGITS
     science
    0.07
     Science
    0.07
    ulf
    0.06
    elle
    0.06
    Science
    0.06
    anto
    0.06
    chemist
    0.06
    loit
    0.06
    uitka
    0.06
    673
    0.06
    Activations Density 0.005%

    No Known Activations