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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78334
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to initialization and setup processes

    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
    SETS
    -0.09
    erb
    -0.08
    cats
    -0.07
    ãģĿãģĨ
    -0.07
    .sul
    -0.07
    edException
    -0.07
    IZATION
    -0.07
    olas
    -0.07
    andle
    -0.07
    sla
    -0.07
    POSITIVE LOGITS
    iate
    0.10
    iales
    0.08
    iative
    0.08
    iating
    0.08
    iated
    0.07
    iator
    0.07
    iation
    0.07
    itial
    0.07
    /Foundation
    0.07
    iale
    0.07
    Activations Density 0.017%

    No Known Activations