© 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. 106893
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or notable references associated with people or characters

    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
    ucch
    -0.09
    querque
    -0.07
    issant
    -0.07
    éĻħ
    -0.07
    ouver
    -0.07
     Tape
    -0.07
     Guar
    -0.07
    ünd
    -0.07
    Runner
    -0.06
     Hew
    -0.06
    POSITIVE LOGITS
     Nov
    0.07
    ener
    0.07
     Contrib
    0.06
    ại
    0.06
     Sal
    0.06
    orest
    0.06
    arem
    0.06
     Sab
    0.06
    igy
    0.06
     Str
    0.06
    Activations Density 0.001%

    No Known Activations