© 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. 104764
    Prev
    Next
    INDEX
    Explanations

    ideas related to conceptual discussions and their evaluations

    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
     technik
    -0.07
    gow
    -0.07
    ellt
    -0.07
    तर
    -0.07
    noop
    -0.07
    isu
    -0.06
    rana
    -0.06
     ordin
    -0.06
    оÑĢоÑĤ
    -0.06
    _SCENE
    -0.06
    POSITIVE LOGITS
     ideas
    0.14
    ideas
    0.14
     Ideas
    0.13
    idea
    0.11
     Idea
    0.11
     idea
    0.11
    .idea
    0.09
     thoughts
    0.08
     Thoughts
    0.08
     concepts
    0.08
    Activations Density 0.052%

    No Known Activations