© 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. 94968
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online platforms, particularly LinkedIn

    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
    _ATOM
    -0.06
    gal
    -0.06
    Requirements
    -0.06
    -valu
    -0.06
     Cres
    -0.06
    swer
    -0.06
    RU
    -0.06
    536
    -0.06
    dic
    -0.06
    vou
    -0.06
    POSITIVE LOGITS
    emale
    0.07
     profile
    0.07
     LinkedIn
    0.07
     Lod
    0.06
     Profile
    0.06
    uka
    0.06
    upy
    0.06
    unga
    0.06
    iggs
    0.06
    LinkedIn
    0.06
    Activations Density 0.003%

    No Known Activations