© 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. 4464
    Prev
    Next
    INDEX
    Explanations

    references to events and competitions

    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
    asca
    -0.08
    ÑĪев
    -0.07
    .Formatting
    -0.07
    udu
    -0.07
    å±
    -0.07
    ugins
    -0.07
     porad
    -0.06
    ADV
    -0.06
    .resume
    -0.06
    .jd
    -0.06
    POSITIVE LOGITS
     during
    0.17
    during
    0.14
     During
    0.13
     lors
    0.13
     attending
    0.12
     durante
    0.12
    During
    0.12
     participating
    0.11
     upcoming
    0.10
     at
    0.10
    Activations Density 0.240%

    No Known Activations