© 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. 75133
    Prev
    Next
    INDEX
    Explanations

    relative clauses and conjunctions

    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
    alle
    -0.07
     termed
    -0.07
     Called
    -0.07
    {{{
    -0.06
     Animalia
    -0.06
    511
    -0.06
    anner
    -0.06
    indsight
    -0.06
    пон
    -0.06
    yen
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģ
    0.08
     consists
    0.07
    æĺ¯ä¸Ģ个
    0.07
     consist
    0.07
    cons
    0.07
     merupakan
    0.07
     basically
    0.07
    oland
    0.06
     isa
    0.06
    arer
    0.06
    Activations Density 0.035%

    No Known Activations