© 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. 40462
    Prev
    Next
    INDEX
    Explanations

    terms related to continuity and disruption

    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
    ullan
    -0.07
    zim
    -0.07
     ÎĶι
    -0.07
    ULE
    -0.07
    zell
    -0.07
    coles
    -0.07
    afen
    -0.06
    ÄĻd
    -0.06
    CTS
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
    ilos
    0.07
    ÅĤo
    0.06
    lo
    0.06
    soon
    0.06
    354
    0.06
    ust
    0.06
    tml
    0.06
    got
    0.05
    rowse
    0.05
    gas
    0.05
    Activations Density 0.001%

    No Known Activations