© 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. 128685
    Prev
    Next
    INDEX
    Explanations

    negative implications related to lack of presence or participation

    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
     hakk
    -0.07
    ritch
    -0.07
    é³
    -0.07
    殿
    -0.07
    ÐłÐĿ
    -0.06
    gesch
    -0.06
    enties
    -0.06
     Hakk
    -0.06
    iations
    -0.06
    ">ÃĹ</
    -0.06
    POSITIVE LOGITS
     since
    0.13
    since
    0.11
     ever
    0.10
    Since
    0.10
     Since
    0.10
    _since
    0.09
     anymore
    0.09
     anything
    0.09
     any
    0.09
    ever
    0.08
    Activations Density 0.018%

    No Known Activations