© 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 EvalsExportsinterp-engineNEWAPI 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. 38832
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between structures or systems

    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
     góc
    -0.07
    جع
    -0.07
     kav
    -0.07
    ucha
    -0.07
    inch
    -0.07
     KeyValuePair
    -0.07
    elerik
    -0.07
    StateException
    -0.06
     lee
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
     via
    0.10
    -connect
    0.09
    via
    0.09
     bridges
    0.09
    Via
    0.09
     brid
    0.08
     connecting
    0.08
     Via
    0.08
     connect
    0.08
     link
    0.08
    Activations Density 0.018%

    No Known Activations