© 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. 15245
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or exceptions in statements

    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
    uner
    -0.08
    rente
    -0.07
    umpt
    -0.07
    ivery
    -0.07
    æģ
    -0.07
    ordes
    -0.06
    udder
    -0.06
     Toilet
    -0.06
    amines
    -0.06
    .addElement
    -0.06
    POSITIVE LOGITS
     currently
    0.08
     unlikely
    0.08
     presently
    0.08
    currently
    0.08
    unlikely
    0.08
    缮åīį
    0.07
    likelihood
    0.07
     initial
    0.07
    sing
    0.07
     initially
    0.07
    Activations Density 0.021%

    No Known Activations