© 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. 80443
    Prev
    Next
    INDEX
    Explanations

    sentences emphasizing obligations or expectations

    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
    ål
    -0.07
    imbus
    -0.07
    anc
    -0.06
     did
    -0.06
    irut
    -0.06
    interop
    -0.06
    nici
    -0.06
     actual
    -0.06
    idis
    -0.06
    instr
    -0.06
    POSITIVE LOGITS
     will
    0.23
    will
    0.20
     sẽ
    0.19
    'll
    0.18
    æľĥ
    0.17
     akan
    0.17
    ’ll
    0.17
    ä¼ļ
    0.17
    Will
    0.17
     bÄĻdzie
    0.16
    Activations Density 0.114%

    No Known Activations