© 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. 127942
    Prev
    Next
    INDEX
    Explanations

    personal reflections and memories regarding cinematic experiences

    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
    ildo
    -0.07
    çĿĽ
    -0.06
     Beit
    -0.06
    åģ·
    -0.06
    ạn
    -0.06
    ç·Ĭ
    -0.06
    usting
    -0.06
    åı·
    -0.06
    resh
    -0.06
    cripts
    -0.06
    POSITIVE LOGITS
    aki
    0.06
    IME
    0.06
     exact
    0.06
    exact
    0.06
    ¤íĶĦ
    0.06
    ساس
    0.06
    Search
    0.06
    .setParent
    0.06
    åı¯èĥ½æĢ§
    0.06
    ÎŃÏģ
    0.06
    Activations Density 0.006%

    No Known Activations