© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    names of authors and literary works

    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
    avl
    -0.07
    IMS
    -0.06
    305
    -0.06
    ury
    -0.06
     IMS
    -0.06
    NC
    -0.06
    apiro
    -0.06
    orte
    -0.06
    æĸ¹
    -0.06
    ikit
    -0.06
    POSITIVE LOGITS
     Hugo
    0.08
     sf
    0.08
     SF
    0.08
    SF
    0.08
     science
    0.08
     Haj
    0.07
     Science
    0.07
    ansible
    0.07
    .sf
    0.07
    science
    0.07
    Activations Density 0.167%

    No Known Activations