© 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. 15321
    Prev
    Next
    INDEX
    Explanations

    sequences and syntax typically used in programming code or markup languages

    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
    625
    -0.06
     kl
    -0.06
     trib
    -0.06
     ----------------------------------------------------------------------------------------------------------------
    -0.06
     pl
    -0.05
    enberg
    -0.05
    iment
    -0.05
     Meh
    -0.05
    iments
    -0.05
     alphabet
    -0.05
    POSITIVE LOGITS
    zano
    0.07
    łģ
    0.07
    gebung
    0.07
    é«
    0.07
    ymoon
    0.07
    âķIJâķIJ
    0.07
    RequestMethod
    0.07
    ombo
    0.07
    477
    0.06
    ModelProperty
    0.06
    Activations Density 0.037%

    No Known Activations