© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90828
    Prev
    Next
    INDEX
    Explanations

    sections or elements of HTML or code

    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
     Brend
    -0.06
    W
    -0.05
    athe
    -0.05
    ec
    -0.05
    ↵↵
    -0.05
    u
    -0.05
     Dem
    -0.05
    eki
    -0.05
     can
    -0.05
     cent
    -0.05
    POSITIVE LOGITS
    sonian
    0.08
    ãĤĮãģ©
    0.08
    mods
    0.08
    ikal
    0.07
    htub
    0.07
    rador
    0.07
     ogs
    0.07
    ulong
    0.07
    ftype
    0.07
    år
    0.07
    Activations Density 0.007%

    No Known Activations