© 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 EvalsExportsAPI 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. 82999
    Prev
    Next
    INDEX
    Explanations

    references to vinyl products such as records or materials

    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
    ients
    -0.07
    ÑĢек
    -0.07
    een
    -0.07
    itel
    -0.06
    enheim
    -0.06
    ekk
    -0.06
    ÙħÙĩ
    -0.06
    illon
    -0.06
     diren
    -0.06
    fcc
    -0.06
    POSITIVE LOGITS
    ized
    0.10
    zier
    0.09
    izar
    0.08
    s
    0.08
    ization
    0.08
    erea
    0.07
    mania
    0.07
    icious
    0.07
    scape
    0.07
    ãĥ¼ãĥĪ
    0.07
    Activations Density 0.003%

    No Known Activations