© 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. 71170
    Prev
    Next
    INDEX
    Explanations

    actions related to teaching, assisting, and supporting others

    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
     ours
    -0.07
    arest
    -0.07
    rax
    -0.07
    ebin
    -0.07
    siz
    -0.06
    ÑĪий
    -0.06
    ’S
    -0.06
    ieur
    -0.06
    irket
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
     them
    0.18
     their
    0.16
    ä»ĸ们
    0.14
     they
    0.14
     ihnen
    0.14
    ä»ĸåĢij
    0.13
     иÑħ
    0.13
    their
    0.13
     loro
    0.12
    them
    0.12
    Activations Density 0.086%

    No Known Activations