© 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. 92598
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names associated with scientific or technical 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
    ิà¸Ĺย
    -0.06
    ewed
    -0.06
    itten
    -0.06
     spo
    -0.06
    roe
    -0.06
    inde
    -0.06
    ure
    -0.06
    refs
    -0.06
    stead
    -0.06
    lb
    -0.05
    POSITIVE LOGITS
    æ®
    0.07
    odyn
    0.07
    imers
    0.07
    phia
    0.07
    é»İ
    0.07
    ãĤº
    0.07
    lectron
    0.07
     impro
    0.07
    bracht
    0.06
    olik
    0.06
    Activations Density 0.122%

    No Known Activations