© 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. 79532
    Prev
    Next
    INDEX
    Explanations

    negative phrases or concepts related to action or behavior

    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
     proof
    -0.10
     Proof
    -0.10
    _proof
    -0.09
    Proof
    -0.09
    proof
    -0.09
     proofs
    -0.08
    -proof
    -0.08
    lef
    -0.07
     hum
    -0.06
     mest
    -0.06
    POSITIVE LOGITS
     anything
    0.09
    Anything
    0.09
    anything
    0.09
     Anything
    0.08
    Wunused
    0.07
     slightest
    0.07
    ucer
    0.06
    icaret
    0.06
     Flyers
    0.06
    edis
    0.06
    Activations Density 0.035%

    No Known Activations