© 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. 15523
    Prev
    Next
    INDEX
    Explanations

    references to titles and names in the text

    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
    iá»ĩp
    -0.07
    erne
    -0.07
    oại
    -0.07
     имÑĥ
    -0.07
    нож
    -0.07
    heim
    -0.07
    물ìĿĦ
    -0.07
    modo
    -0.07
    åľŃ
    -0.07
    ordon
    -0.07
    POSITIVE LOGITS
    plate
    0.10
    plates
    0.09
    ake
    0.09
     change
    0.08
    éĢļãĤĬ
    0.08
    change
    0.07
    /title
    0.07
    ì§ĵ
    0.06
     plate
    0.06
     changed
    0.06
    Activations Density 0.019%

    No Known Activations