© 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. 125015
    Prev
    Next
    INDEX
    Explanations

    references to items and their attributes in a database or list

    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
     fluid
    -0.06
    idor
    -0.06
    166
    -0.06
     vent
    -0.06
     functioning
    -0.06
     aw
    -0.06
    ako
    -0.06
     tab
    -0.06
    icont
    -0.06
    ardon
    -0.06
    POSITIVE LOGITS
     matching
    0.09
    matching
    0.08
    åĮ¹
    0.08
     matches
    0.07
     Matching
    0.07
    Bear
    0.07
    Matching
    0.07
    ongoose
    0.07
    bear
    0.07
    match
    0.07
    Activations Density 0.025%

    No Known Activations