© 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. 120786
    Prev
    Next
    INDEX
    Explanations

    citation information, particularly from academic publications and research articles

    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
    æ°Ĺ
    -0.07
    ses
    -0.07
    ÄĽt
    -0.07
    oÄį
    -0.06
    anda
    -0.06
    ãģijãĤĮãģ©
    -0.06
    malink
    -0.06
     ÙĤÙĪÙĦ
    -0.06
    DRV
    -0.06
    Versions
    -0.06
    POSITIVE LOGITS
    uro
    0.06
    uer
    0.06
    jk
    0.06
    gfx
    0.06
    Breadcrumb
    0.05
    silver
    0.05
     PU
    0.05
    _processes
    0.05
     Bour
    0.05
    даÑĤ
    0.05
    Activations Density 0.009%

    No Known Activations