© 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. 119637
    Prev
    Next
    INDEX
    Explanations

    references to media content and programming

    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
    lád
    -0.07
    afen
    -0.07
    ILED
    -0.07
    ãĥ¡ãĥ©
    -0.07
    451
    -0.07
     LoÃłi
    -0.07
    ãĥ³ãĥĶ
    -0.07
    ramer
    -0.07
     @}
    -0.07
     ÑģÑħод
    -0.06
    POSITIVE LOGITS
     programming
    0.09
     content
    0.07
    programs
    0.07
    Programming
    0.07
     programmes
    0.07
     Programming
    0.06
     programs
    0.06
     station
    0.06
     services
    0.06
     monopoly
    0.06
    Activations Density 0.006%

    No Known Activations