© 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. 108061
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and contractual 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
    виж
    -0.07
    orton
    -0.07
    ALCHEMY
    -0.07
    reste
    -0.07
    onda
    -0.06
     virt
    -0.06
    idend
    -0.06
     nedir
    -0.06
    (enabled
    -0.06
    .optional
    -0.06
    POSITIVE LOGITS
     prior
    0.07
    .sales
    0.06
     pub
    0.06
    inton
    0.06
     pubs
    0.06
    æĶ¾
    0.06
    .idea
    0.06
     earliest
    0.06
     Gore
    0.05
    owitz
    0.05
    Activations Density 0.001%

    No Known Activations