© 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. 87561
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     Mori
    -0.06
    uel
    -0.06
     Garner
    -0.06
    SS
    -0.06
    w
    -0.06
    tron
    -0.06
    pi
    -0.06
     yard
    -0.05
    nat
    -0.05
    .expr
    -0.05
    POSITIVE LOGITS
    _pb
    0.07
    venues
    0.07
    adal
    0.07
    eç
    0.07
    iterated
    0.07
    adir
    0.07
    jem
    0.07
    .har
    0.07
    alice
    0.07
    -FIRST
    0.07
    Activations Density 0.002%

    No Known Activations