© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    connections and relationships within scientific or technical information

    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
    obec
    -0.07
     Ulus
    -0.06
    eres
    -0.06
    cores
    -0.06
    UA
    -0.06
    afe
    -0.05
    492
    -0.05
     Patel
    -0.05
    Question
    -0.05
    iet
    -0.05
    POSITIVE LOGITS
    रण
    0.08
    ÑĦоÑĢми
    0.07
    (=)
    0.07
    thritis
    0.07
    ologne
    0.07
    anguages
    0.06
    sched
    0.06
     skal
    0.06
     Mueller
    0.06
    ëŀ
    0.06
    Activations Density 0.103%

    No Known Activations