© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87061
    Prev
    Next
    INDEX
    Explanations

    associations with web links and references to online resources

    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
    irt
    -0.07
    endra
    -0.06
    unes
    -0.06
    licit
    -0.06
    angler
    -0.06
    oog
    -0.06
    clus
    -0.06
    dro
    -0.06
    aney
    -0.06
    sdale
    -0.06
    POSITIVE LOGITS
    .sourceforge
    0.08
     gratuiti
    0.07
     homepage
    0.07
     software
    0.07
    Software
    0.07
     www
    0.07
     Software
    0.07
    Escort
    0.06
    ypi
    0.06
     bordel
    0.06
    Activations Density 0.030%

    No Known Activations