© 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. 129582
    Prev
    Next
    INDEX
    Explanations

    configuration options related to file paths and 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
    airo
    -0.08
    rai
    -0.08
    duct
    -0.07
    illet
    -0.07
    alis
    -0.06
    >NN
    -0.06
    .IsMatch
    -0.06
    áÄį
    -0.06
    fty
    -0.06
    eks
    -0.06
    POSITIVE LOGITS
    edReader
    0.07
    Stuff
    0.07
    IDX
    0.06
    знаÑĩа
    0.06
    0.06
    ãĤ¿ãĥ¼
    0.06
    scribe
    0.06
    Äħd
    0.06
    ä¸Ģç·Ĵ
    0.06
    ãģĿ
    0.06
    Activations Density 0.005%

    No Known Activations