© 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. 15-LLAMASCOPE-RES-131K
    11. 86745
    Prev
    Next
    INDEX
    Explanations

    the word "only" and its variants

    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
    onte
    -0.07
    chn
    -0.06
     unin
    -0.06
    atsu
    -0.06
    gs
    -0.06
    -0.05
    wen
    -0.05
    164
    -0.05
    enu
    -0.05
     crossword
    -0.05
    POSITIVE LOGITS
    anje
    0.08
     же
    0.08
    /Set
    0.07
     váºŃy
    0.07
    Mahon
    0.06
    htdocs
    0.06
    cth
    0.06
    -caption
    0.06
     пÑĢоÑĩ
    0.06
    ấn
    0.06
    Activations Density 0.004%

    No Known Activations