© 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. 120860
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and sentence endings

    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
    otts
    -0.08
    parator
    -0.07
    imator
    -0.07
    ujemy
    -0.07
    опиÑģ
    -0.07
    emain
    -0.07
    GuidId
    -0.07
    orrent
    -0.07
    ık
    -0.07
    andon
    -0.07
    POSITIVE LOGITS
     Sp
    0.07
     still
    0.07
     bottom
    0.07
    er
    0.06
    ijken
    0.06
     some
    0.06
     point
    0.06
     Bottom
    0.06
     fut
    0.06
    erin
    0.06
    Activations Density 0.016%

    No Known Activations