© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97426
    Prev
    Next
    INDEX
    Explanations

    brackets and special formatting symbols used in technical documents

    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
    gid
    -0.06
    ostel
    -0.06
    unami
    -0.06
    usercontent
    -0.06
    PCR
    -0.06
     Lazy
    -0.06
    дÑı
    -0.06
    akte
    -0.06
     voks
    -0.06
    lesi
    -0.06
    POSITIVE LOGITS
    /up
    0.06
    esor
    0.06
    ÙĨج
    0.06
    alcon
    0.06
     uchar
    0.06
    .compat
    0.06
     tack
    0.06
    /team
    0.06
     Mozart
    0.06
     ZEND
    0.06
    Activations Density 0.001%

    No Known Activations