© 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. 55737
    Prev
    Next
    INDEX
    Explanations

    words related to constraints and conditions

    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
    essen
    -0.07
    ÏĥÏħ
    -0.07
    oref
    -0.07
    EFR
    -0.06
    æ²Ī
    -0.06
     ÎijÏģ
    -0.06
    μβ
    -0.06
     státu
    -0.06
    _contrib
    -0.06
    thood
    -0.06
    POSITIVE LOGITS
     require
    0.10
     requires
    0.09
     whose
    0.09
     requiring
    0.08
    requ
    0.08
    ÄįÃŃ
    0.08
     requ
    0.07
     Require
    0.07
     Requires
    0.07
    whose
    0.07
    Activations Density 0.046%

    No Known Activations