© 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. 41559
    Prev
    Next
    INDEX
    Explanations

    negation and terms related to absence or non-existence

    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
    owi
    -0.09
    launcher
    -0.08
    istrovstvÃŃ
    -0.08
    ÅĻÃŃm
    -0.08
    entiful
    -0.07
    OUS
    -0.07
    orgia
    -0.07
    asn
    -0.07
    маз
    -0.07
    ertia
    -0.07
    POSITIVE LOGITS
     Simpl
    0.08
     already
    0.07
     too
    0.07
     simultaneously
    0.06
     harm
    0.06
     contr
    0.06
    arin
    0.06
    ch
    0.05
    Ìĥ
    0.05
    atter
    0.05
    Activations Density 0.054%

    No Known Activations