© 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. 17-LLAMASCOPE-RES-131K
    6. 28813
    Prev
    Next
    INDEX
    Explanations

    specific years and time-related details in a 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
    istributed
    -0.07
    archs
    -0.07
     Distributed
    -0.06
    oles
    -0.06
    ContextHolder
    -0.06
    otron
    -0.06
    å»
    -0.06
    meni
    -0.06
    illas
    -0.06
    -election
    -0.06
    POSITIVE LOGITS
     founded
    0.10
     formation
    0.10
    Formation
    0.09
     Formation
    0.09
     formed
    0.09
     founders
    0.09
     Founded
    0.08
     founding
    0.08
    Founded
    0.08
     founder
    0.07
    Activations Density 0.046%

    No Known Activations