© 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. 40703
    Prev
    Next
    INDEX
    Explanations

    concepts related to scalability in engineering and technology

    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
     بÙĪابة
    -0.07
    eprom
    -0.07
    ATAB
    -0.07
    æ¿ĥ
    -0.07
    rypton
    -0.07
    访
    -0.07
    ANDING
    -0.07
    rint
    -0.07
    .'/'.$
    -0.07
    CTYPE
    -0.06
    POSITIVE LOGITS
     scale
    0.09
     scaling
    0.08
     large
    0.08
     distributed
    0.07
     LARGE
    0.07
     scalability
    0.07
    100
    0.07
     scalable
    0.06
     Scale
    0.06
     rack
    0.06
    Activations Density 0.046%

    No Known Activations