© 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. 86159
    Prev
    Next
    INDEX
    Explanations

    various references to comparative terms and concepts

    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
    vision
    -0.07
    ãĤ·ãĤ¢
    -0.06
    borg
    -0.06
    _lng
    -0.06
     moci
    -0.06
    alse
    -0.06
    ignal
    -0.06
    ียà¸Ļ
    -0.06
    æĬķ
    -0.06
    imest
    -0.06
    POSITIVE LOGITS
     thing
    0.11
     Thing
    0.08
    Thing
    0.08
    thing
    0.07
     reason
    0.07
    entine
    0.07
    =\"/
    0.07
    (thing
    0.07
    raison
    0.07
     equally
    0.06
    Activations Density 0.013%

    No Known Activations