© 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. 128663
    Prev
    Next
    INDEX
    Explanations

    phrases related to applications and their processing requirements

    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
     Ore
    -0.06
     Kral
    -0.06
    woo
    -0.06
     dreams
    -0.06
     desperation
    -0.06
    644
    -0.06
    wald
    -0.05
    isted
    -0.05
    ÑĤал
    -0.05
     taj
    -0.05
    POSITIVE LOGITS
    busy
    0.08
    æħİ
    0.08
     slower
    0.08
    APO
    0.07
    _complex
    0.07
     gấp
    0.07
    urat
    0.07
    è¦ģ
    0.07
    ething
    0.07
     phức
    0.07
    Activations Density 0.035%

    No Known Activations