© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 604
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or codes related to publications and citations

    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
    íĭ
    -0.06
    rior
    -0.06
     vis
    -0.06
    zs
    -0.06
     cle
    -0.06
    loit
    -0.06
     Gig
    -0.05
     Capitals
    -0.05
    vester
    -0.05
     Burr
    -0.05
    POSITIVE LOGITS
    inspace
    0.07
    agy
    0.07
    kB
    0.07
    /gui
    0.07
     McKay
    0.07
    upal
    0.07
    Interop
    0.07
    hte
    0.06
    <location
    0.06
    aminer
    0.06
    Activations Density 0.044%

    No Known Activations