© 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. 125868
    Prev
    Next
    INDEX
    Explanations

    references to empty states or conditions in code

    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
    eria
    -0.07
    iqueta
    -0.07
    yo
    -0.07
    bsolute
    -0.06
    ivel
    -0.06
    ctl
    -0.06
    ÅŁÄ±
    -0.06
    iza
    -0.06
    amar
    -0.06
    getic
    -0.06
    POSITIVE LOGITS
    /null
    0.08
    ness
    0.07
    /full
    0.07
    -handed
    0.07
    272
    0.07
    ä¸Ķ
    0.07
    gest
    0.07
    /no
    0.06
    urst
    0.06
    ETYPE
    0.06
    Activations Density 0.013%

    No Known Activations