© 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. 79074
    Prev
    Next
    INDEX
    Explanations

    terms related to offerings, features, and activities in various contexts

    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
     yani
    -0.08
    regor
    -0.07
    atism
    -0.07
    kuk
    -0.07
    uide
    -0.06
    ｡
    -0.06
    ammen
    -0.06
     ÑĥÑģÑĤÑĢа
    -0.06
    ayne
    -0.06
    áÄį
    -0.06
    POSITIVE LOGITS
     several
    0.12
     two
    0.10
    two
    0.10
    Several
    0.09
     Several
    0.09
     also
    0.08
    three
    0.08
     three
    0.08
    also
    0.08
    Two
    0.08
    Activations Density 0.033%

    No Known Activations