© 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. 78801
    Prev
    Next
    INDEX
    Explanations

    phrases and predictions about future trends and developments

    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
    ettel
    -0.08
    beck
    -0.06
    unter
    -0.06
     thereby
    -0.06
    رÛĮز
    -0.06
     plummet
    -0.06
    lla
    -0.06
    afari
    -0.06
    ill
    -0.06
     Rein
    -0.06
    POSITIVE LOGITS
     further
    0.13
    继ç»Ń
    0.12
     continue
    0.12
     future
    0.11
     continues
    0.11
     weitere
    0.11
    continue
    0.11
    Continue
    0.10
     continued
    0.10
     continuation
    0.10
    Activations Density 0.027%

    No Known Activations