© 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. 75856
    Prev
    Next
    INDEX
    Explanations

    terms related to clothing and identity markers

    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
    aber
    -0.09
    ãĥ¼ãĥģ
    -0.08
    ixer
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    UNE
    -0.07
    _regularizer
    -0.07
    oles
    -0.07
    istor
    -0.07
    ypsum
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
    ed
    0.13
    ting
    0.09
    ted
    0.08
    edl
    0.07
    med
    0.07
    ded
    0.07
    ved
    0.06
    red
    0.06
    edback
    0.06
    ropic
    0.06
    Activations Density 0.001%

    No Known Activations