© 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. 82062
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and phrases indicating agreement or disagreement

    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
    .scalablytyped
    -0.09
    OfSize
    -0.07
    oÄį
    -0.07
    аном
    -0.07
    cratch
    -0.07
    _unset
    -0.07
    omap
    -0.07
    792
    -0.07
    uÅŁ
    -0.07
    áºł
    -0.07
    POSITIVE LOGITS
     lots
    0.12
     no
    0.10
     plenty
    0.09
    lots
    0.09
     Lots
    0.09
    Lots
    0.08
     =
    0.07
     always
    0.06
    rai
    0.06
     keine
    0.06
    Activations Density 0.071%

    No Known Activations