© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87737
    Prev
    Next
    INDEX
    Explanations

    processes and methods related to data transformation and combination

    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
    /ros
    -0.08
    reen
    -0.08
    amer
    -0.08
     ÙħÙĪÙĨ
    -0.07
    θο
    -0.07
    tej
    -0.07
    iscard
    -0.07
    zos
    -0.07
    QueryBuilder
    -0.07
    _AI
    -0.07
    POSITIVE LOGITS
     forming
    0.11
     resulting
    0.11
     create
    0.10
     creates
    0.10
     produces
    0.10
     produce
    0.09
     creating
    0.09
     producing
    0.09
     form
    0.09
     forms
    0.08
    Activations Density 0.058%

    No Known Activations