© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29391
    Prev
    Next
    INDEX
    Explanations

    instances of comment sections or references to comments within text

    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
    abo
    -0.07
    éĸ¢
    -0.07
    INCT
    -0.07
    оже
    -0.07
    lets
    -0.07
    olas
    -0.07
    emu
    -0.07
    ouch
    -0.06
    oo
    -0.06
    åIJį
    -0.06
    POSITIVE LOGITS
    µ
    0.07
    istrar
    0.06
     Off
    0.06
    GenerationStrategy
    0.06
    dub
    0.06
    erosis
    0.06
     trace
    0.06
    oref
    0.06
    issors
    0.06
    rong
    0.06
    Activations Density 0.003%

    No Known Activations