© 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. 118503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating organizational commitment and growth

    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
    och
    -0.07
    iya
    -0.07
    áte
    -0.07
    elease
    -0.06
     vice
    -0.06
    FML
    -0.06
     eventual
    -0.06
    _overflow
    -0.06
    EdgeInsets
    -0.06
     Discovery
    -0.06
    POSITIVE LOGITS
     commitment
    0.10
     commitments
    0.07
     Commit
    0.07
     continue
    0.07
     divers
    0.06
    ihn
    0.06
     continued
    0.06
    zek
    0.06
    continue
    0.06
    .shtml
    0.06
    Activations Density 0.024%

    No Known Activations