© 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. 76421
    Prev
    Next
    INDEX
    Explanations

    concepts related to various fields of study and practical skills

    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
    innen
    -0.08
    jez
    -0.07
    alama
    -0.07
    abbr
    -0.07
    atee
    -0.07
    quier
    -0.07
    apes
    -0.07
    uck
    -0.06
    ril
    -0.06
    acier
    -0.06
    POSITIVE LOGITS
    such
    0.07
    582
    0.07
     via
    0.06
     Specifically
    0.06
     such
    0.06
    ucc
    0.06
    369
    0.06
     Twice
    0.06
    -ending
    0.06
     sourceMapping
    0.06
    Activations Density 0.048%

    No Known Activations