© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119839
    Prev
    Next
    INDEX
    Explanations

    references to web domains and specifically mentions of Google's and Amazon's URLs

    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
    uar
    -0.07
    uild
    -0.06
    aceae
    -0.06
    仲
    -0.06
    dge
    -0.06
    ures
    -0.06
    uilt
    -0.06
    à¤Ĩ
    -0.06
    ucci
    -0.06
    emens
    -0.06
    POSITIVE LOGITS
    izado
    0.07
    edla
    0.07
    _HOOK
    0.07
    »
    0.07
    uso
    0.07
     Anchor
    0.06
    .scalablytyped
    0.06
    haf
    0.06
    irmed
    0.06
    ering
    0.06
    Activations Density 0.002%

    No Known Activations