Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44249
    Prev
    Next
    INDEX
    Explanations

    special characters or non-standard symbols 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
     Portuguese
    -0.07
     Spanish
    -0.06
    awan
    -0.06
    ohon
    -0.06
    Spanish
    -0.06
    cycl
    -0.06
     Stout
    -0.06
     espan
    -0.06
     Portsmouth
    -0.06
     latino
    -0.06
    POSITIVE LOGITS
     Ep
    0.13
     DEA
    0.12
     Cam
    0.11
    Ep
    0.11
     Teresa
    0.10
     Brenda
    0.10
     Dallas
    0.09
     drug
    0.09
     drugs
    0.09
     narcotics
    0.09
    Activations Density 0.003%

    No Known Activations