© 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. 125776
    Prev
    Next
    INDEX
    Explanations

    terms related to discounts and promotions

    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
    ahir
    -0.08
    @\
    -0.07
    è³¢
    -0.07
    ảo
    -0.07
    @brief
    -0.07
    emode
    -0.07
     Ziel
    -0.07
    eniz
    -0.07
    å·»
    -0.06
    azel
    -0.06
    POSITIVE LOGITS
     codes
    0.08
     code
    0.08
    ÙĪات
    0.08
    -code
    0.08
    碼
    0.08
    code
    0.07
     Codes
    0.06
    utter
    0.06
     Code
    0.06
    _code
    0.06
    Activations Density 0.001%

    No Known Activations