© 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. 9-LLAMASCOPE-RES-131K
    11. 95085
    Prev
    Next
    INDEX
    Explanations

    references to musical performances and supporting acts

    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
    fred
    -0.07
    oy
    -0.07
    rong
    -0.06
    uma
    -0.06
     Bilim
    -0.06
    emma
    -0.06
    sher
    -0.06
     Dump
    -0.06
    obox
    -0.06
    ascal
    -0.06
    POSITIVE LOGITS
    attered
    0.06
    Msp
    0.06
    artment
    0.06
    izer
    0.06
     Abs
    0.06
     Rever
    0.06
    patches
    0.06
    actic
    0.06
    ldr
    0.06
    IZER
    0.06
    Activations Density 0.007%

    No Known Activations