© 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. 4030
    Prev
    Next
    INDEX
    Explanations

    negations and disclaimers related to user agreements and copyright policies

    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
    еж
    -0.06
    mos
    -0.06
    _exempt
    -0.06
    sein
    -0.06
    osh
    -0.06
    adol
    -0.06
    TEGER
    -0.06
    adla
    -0.06
    orsche
    -0.06
    ours
    -0.06
    POSITIVE LOGITS
     glo
    0.07
    STA
    0.07
     entitled
    0.06
     rex
    0.06
    Å¡Å¥
    0.06
     chill
    0.06
     im
    0.06
     Ellison
    0.06
    legg
    0.06
     Sto
    0.06
    Activations Density 0.001%

    No Known Activations