© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127204
    Prev
    Next
    INDEX
    Explanations

    instances of significant events or changes in 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
    ummer
    -0.07
    Ñģам
    -0.07
    <boost
    -0.06
    ÏĦÏģι
    -0.06
    .rf
    -0.06
    ži
    -0.06
    oman
    -0.06
     '..',
    -0.06
    .ci
    -0.06
    !;↵
    -0.06
    POSITIVE LOGITS
     ours
    0.17
     yours
    0.12
     ones
    0.11
     theirs
    0.10
     hers
    0.09
     mine
    0.09
    ours
    0.08
    mine
    0.08
     compar
    0.08
     Yours
    0.07
    Activations Density 0.077%

    No Known Activations