© 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. 15-LLAMASCOPE-RES-131K
    11. 88753
    Prev
    Next
    INDEX
    Explanations

    phrases related to definitions or explanations of complex 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
     VERBOSE
    -0.06
    icy
    -0.06
     полÑĮз
    -0.06
    oothing
    -0.06
    uales
    -0.06
    iest
    -0.06
    oplast
    -0.06
    ween
    -0.06
    ulos
    -0.06
    ILING
    -0.06
    POSITIVE LOGITS
     must
    0.21
    must
    0.17
     should
    0.17
     Must
    0.16
     MUST
    0.16
    Must
    0.15
     harus
    0.15
    should
    0.14
     shouldn
    0.14
     должна
    0.14
    Activations Density 0.071%

    No Known Activations