© 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. 88471
    Prev
    Next
    INDEX
    Explanations

    references to the name "Laura"

    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
    mate
    -0.09
    ibo
    -0.09
    eko
    -0.07
    mates
    -0.07
    ÑĢо
    -0.07
    etary
    -0.07
    rate
    -0.07
    º
    -0.06
    PLE
    -0.06
    nes
    -0.06
    POSITIVE LOGITS
    thers
    0.09
    ient
    0.08
    POCH
    0.07
    ic
    0.07
    ollen
    0.07
    ceptar
    0.07
    icine
    0.07
    stry
    0.07
    ÙĩاÛĮ
    0.07
    asso
    0.07
    Activations Density 0.014%

    No Known Activations