© 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. 78402
    Prev
    Next
    INDEX
    Explanations

    the conjunction "that" used in various contexts

    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
    862
    -0.07
    á»ī
    -0.07
    ожд
    -0.07
    лÑĸн
    -0.06
    iro
    -0.06
    onne
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    ijkstra
    -0.06
    arn
    -0.06
    isko
    -0.06
    POSITIVE LOGITS
     recently
    0.08
    oped
    0.06
    oping
    0.06
    flush
    0.06
    /***/
    0.06
    igham
    0.06
    yte
    0.06
    holds
    0.06
     following
    0.06
    ONTAL
    0.06
    Activations Density 0.004%

    No Known Activations