© 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. 106449
    Prev
    Next
    INDEX
    Explanations

    various forms of creative and professional activities

    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
    åı¦å¤ĸ
    -0.08
    ãĥ£
    -0.07
    orer
    -0.07
    radient
    -0.07
    DataExchange
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    -0.07
    jah
    -0.07
    istik
    -0.07
    ialis
    -0.07
    POSITIVE LOGITS
     to
    0.10
     simple
    0.07
    immel
    0.07
     earliest
    0.07
     initial
    0.07
     versus
    0.06
     outset
    0.06
     basics
    0.06
     standpoint
    0.06
     mere
    0.06
    Activations Density 0.046%

    No Known Activations