© 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. 55979
    Prev
    Next
    INDEX
    Explanations

    words related to the presence of verdant or green environments, particularly in an ecological context

    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
    iid
    -0.06
    oter
    -0.06
    NC
    -0.06
    uros
    -0.06
    548
    -0.06
     bÄĽ
    -0.06
    orea
    -0.06
     bump
    -0.06
    Peripheral
    -0.06
    ourd
    -0.06
    POSITIVE LOGITS
    wij
    0.08
    ebra
    0.07
    uster
    0.07
    лÑİд
    0.07
    ifiable
    0.07
    batim
    0.07
     Kidd
    0.07
    anki
    0.07
    amil
    0.06
    isseur
    0.06
    Activations Density 0.028%

    No Known Activations