Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126533
    Prev
    Next
    INDEX
    Explanations

    key terms related to environmental and economic sustainability

    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
    efe
    -0.06
    ayi
    -0.06
    eson
    -0.06
    onte
    -0.06
    oga
    -0.06
    etc
    -0.06
    mediately
    -0.06
    ÃĪ
    -0.06
    å½ĵ
    -0.06
    æ½
    -0.06
    POSITIVE LOGITS
    /Peak
    0.07
     STDCALL
    0.07
     XPAR
    0.07
    mares
    0.07
     showc
    0.07
    503
    0.06
    ahkan
    0.06
    .Arg
    0.06
    (er
    0.06
     Ballard
    0.06
    Activations Density 0.067%

    No Known Activations