© 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. 76766
    Prev
    Next
    INDEX
    Explanations

    terms associated with services, commitments, and client-related interactions, particularly in business contexts

    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
     Berm
    -0.07
     &
    -0.07
     Shell
    -0.07
     intermediary
    -0.07
    ôn
    -0.06
     Barker
    -0.06
     bern
    -0.06
    stown
    -0.06
    rect
    -0.06
     and
    -0.06
    POSITIVE LOGITS
     alike
    0.14
    :animated
    0.08
    nal
    0.07
    abase
    0.07
     stddev
    0.07
     serta
    0.07
    aload
    0.07
    lech
    0.07
    itter
    0.06
    ìļ°ë¦¬
    0.06
    Activations Density 0.061%

    No Known Activations