© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40768
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate adherence to specific guidelines or standards

    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
    wend
    -0.07
    tru
    -0.06
    ikk
    -0.06
    uida
    -0.06
    ÑĭÑģ
    -0.06
    nave
    -0.06
    872
    -0.06
    throp
    -0.06
    utow
    -0.06
    798
    -0.06
    POSITIVE LOGITS
    ogue
    0.07
    ToSelector
    0.07
    رÙĬÙĦ
    0.07
    _Lean
    0.07
    ampus
    0.07
    çħ
    0.07
    ا
    0.07
    obb
    0.07
    anton
    0.07
    antly
    0.06
    Activations Density 0.006%

    No Known Activations