© 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. 74755
    Prev
    Next
    INDEX
    Explanations

    references to scientific models and equations related to less common elements and their properties

    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
    apur
    -0.08
    -0.07
    eless
    -0.07
    agnost
    -0.07
     reverse
    -0.07
    ctl
    -0.06
    964
    -0.06
    ensively
    -0.06
    728
    -0.06
    249
    -0.06
    POSITIVE LOGITS
    âĢį
    0.07
    eco
    0.06
    룴
    0.06
     OPP
    0.06
     incre
    0.06
    िà¤Ń
    0.06
     lục
    0.06
    ÑĢаг
    0.06
    _lastname
    0.06
    ëĭĪìĬ¤
    0.06
    Activations Density 0.101%

    No Known Activations