© 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. 124361
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and their variations

    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
    son
    -0.09
    itude
    -0.08
    y
    -0.08
    sj
    -0.08
    sub
    -0.08
    (er
    -0.08
    ertype
    -0.07
    ych
    -0.07
    ers
    -0.07
    yn
    -0.07
    POSITIVE LOGITS
    -than
    0.30
     than
    0.25
    than
    0.24
    _than
    0.22
     THAN
    0.20
    Than
    0.19
     Than
    0.19
     než
    0.14
    _THAN
    0.14
     niż
    0.14
    Activations Density 0.092%

    No Known Activations