© 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. 17-LLAMASCOPE-RES-131K
    11. 81576
    Prev
    Next
    INDEX
    Explanations

    instances of timestamps or written dates

    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
    akt
    -0.06
    riend
    -0.06
    ourke
    -0.06
     gaps
    -0.06
    io
    -0.06
     Blind
    -0.06
    olesterol
    -0.06
    ptive
    -0.06
    iper
    -0.05
     MLA
    -0.05
    POSITIVE LOGITS
    tea
    0.07
    oup
    0.07
    drv
    0.07
    IME
    0.07
    #ad
    0.07
    \Mapping
    0.06
    zza
    0.06
    pes
    0.06
    UTF
    0.06
    pec
    0.06
    Activations Density 0.003%

    No Known Activations