© 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. 95763
    Prev
    Next
    INDEX
    Explanations

    terms related to audio controls and device settings

    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
    TECTED
    -0.07
    ocz
    -0.06
    actly
    -0.06
    serter
    -0.06
    ored
    -0.06
     abre
    -0.06
    erville
    -0.06
    abile
    -0.06
     lad
    -0.06
    opoly
    -0.06
    POSITIVE LOGITS
    aln
    0.07
    awan
    0.07
    STRU
    0.06
    pras
    0.06
    olist
    0.06
    ennes
    0.06
    \<^
    0.06
    earth
    0.06
     mode
    0.06
    clin
    0.06
    Activations Density 0.009%

    No Known Activations