© 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. 60928
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to searching and discovery

    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
     GOODMAN
    -0.07
     soon
    -0.07
    ÑģÑĤин
    -0.07
    aycast
    -0.07
    688
    -0.06
    زÛĮ
    -0.06
    oped
    -0.06
    nable
    -0.06
    inkel
    -0.06
     Saunders
    -0.06
    POSITIVE LOGITS
     Gone
    0.10
     gone
    0.09
     hadn
    0.09
     changed
    0.09
    gone
    0.09
    changed
    0.08
     telah
    0.08
     already
    0.08
    still
    0.07
     still
    0.07
    Activations Density 0.101%

    No Known Activations