© 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. 54157
    Prev
    Next
    INDEX
    Explanations

    clauses that establish conditions or specify details

    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
    ounc
    -0.08
    ando
    -0.07
    589
    -0.06
     Holl
    -0.06
     Ta
    -0.06
     Consort
    -0.06
     Miche
    -0.06
    pickle
    -0.06
    ruit
    -0.06
    egie
    -0.06
    POSITIVE LOGITS
     æĬķ稿
    0.07
    iento
    0.07
    ình
    0.07
    PERT
    0.06
    umas
    0.06
    oa
    0.06
    haled
    0.06
    OA
    0.06
    ialis
    0.06
    oq
    0.06
    Activations Density 0.015%

    No Known Activations