© 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. 72981
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of opposition

    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
    ekt
    -0.07
    IFI
    -0.06
    aku
    -0.06
    warts
    -0.06
    oksen
    -0.05
    irm
    -0.05
    ubb
    -0.05
    yssey
    -0.05
    ochen
    -0.05
    encil
    -0.05
    POSITIVE LOGITS
     Accept
    0.11
    Accept
    0.10
    accept
    0.09
    _accept
    0.09
     accept
    0.09
     ACCEPT
    0.08
     acceptance
    0.08
     accepting
    0.08
     acept
    0.08
     souhlas
    0.08
    Activations Density 0.032%

    No Known Activations