© 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. 85652
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate important information or the necessity of notes

    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
    741
    -0.06
    onet
    -0.06
    CAM
    -0.06
    ÌĪ
    -0.06
    aml
    -0.06
    kami
    -0.06
    cam
    -0.06
     Bubble
    -0.06
    oyo
    -0.05
    KeyName
    -0.05
    POSITIVE LOGITS
     note
    0.14
    note
    0.11
     Note
    0.10
     noted
    0.10
    Note
    0.10
    .note
    0.09
    -note
    0.09
     notes
    0.09
    _note
    0.09
    (note
    0.09
    Activations Density 0.018%

    No Known Activations