© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 817
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods and historical context

    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
    uzzle
    -0.07
    оÑĤÑĮ
    -0.07
    udget
    -0.07
    /TT
    -0.07
     escorte
    -0.06
    .tm
    -0.06
    otts
    -0.06
    iž
    -0.06
    FML
    -0.06
    ziej
    -0.06
    POSITIVE LOGITS
     Memories
    0.08
     memories
    0.08
     Mem
    0.08
     remembers
    0.07
    mem
    0.07
     remembered
    0.07
     remember
    0.07
     era
    0.07
    _memory
    0.07
     memory
    0.07
    Activations Density 0.049%

    No Known Activations