© 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. 15-LLAMASCOPE-RES-131K
    11. 62430
    Prev
    Next
    INDEX
    Explanations

    mentions of performance-related activities or events

    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
    shot
    -0.08
    orna
    -0.08
    ulin
    -0.07
    ness
    -0.07
    ward
    -0.07
    quet
    -0.07
    rint
    -0.07
    ethod
    -0.07
    ill
    -0.07
    arg
    -0.07
    POSITIVE LOGITS
    ables
    0.08
    WER
    0.07
    /display
    0.07
    /install
    0.07
    lint
    0.07
    ModelIndex
    0.06
    EDIUM
    0.06
    able
    0.06
    RICT
    0.06
    물
    0.06
    Activations Density 0.040%

    No Known Activations