© 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. 95643
    Prev
    Next
    INDEX
    Explanations

    information about hotel policies and charges

    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
    trib
    -0.06
    ncia
    -0.06
     tá»Ń
    -0.05
     RD
    -0.05
    azz
    -0.05
    ne
    -0.05
     Celsius
    -0.05
     Brah
    -0.05
    Ce
    -0.05
     signalling
    -0.05
    POSITIVE LOGITS
    ewith
    0.08
    .Compiler
    0.08
    mojom
    0.07
    odash
    0.07
    ales
    0.07
     Nested
    0.07
    ัà¸ģà¸ģ
    0.07
    stroy
    0.07
    ĥ
    0.06
     kindly
    0.06
    Activations Density 0.016%

    No Known Activations