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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95984
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface components in 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
    oter
    -0.07
     fol
    -0.06
     Fol
    -0.06
     vit
    -0.06
    ÑģÑĤÑĢ
    -0.06
     Socket
    -0.06
    ix
    -0.06
    ogle
    -0.06
    itty
    -0.06
    onym
    -0.06
    POSITIVE LOGITS
     ucwords
    0.08
    istine
    0.07
    ehler
    0.07
    shaw
    0.06
    ког
    0.06
    ãģ¡ãģ¯
    0.06
    jezd
    0.06
    ãģ°ãģĭãĤĬ
    0.06
    ä¹ĭä¸Ģ
    0.06
    езда
    0.06
    Activations Density 0.002%

    No Known Activations