© 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. 85332
    Prev
    Next
    INDEX
    Explanations

    phrases related to change and transformation

    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
    ži
    -0.06
    ungle
    -0.06
    Nav
    -0.06
     overall
    -0.06
    uiltin
    -0.06
    ownt
    -0.05
    usch
    -0.05
     Kear
    -0.05
    jist
    -0.05
    evi
    -0.05
    POSITIVE LOGITS
     kind
    0.11
     sort
    0.11
     sorts
    0.09
    éĤ£ç§į
    0.09
     kinds
    0.09
    kind
    0.09
    sort
    0.08
    ãĥ¼ãĥĨ
    0.07
    ÏĦον
    0.07
     KIND
    0.07
    Activations Density 0.077%

    No Known Activations