© 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 EvalsExportsAPI 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. 16507
    Prev
    Next
    INDEX
    Explanations

    instances of emoticons or symbols used in informal communication

    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
    skirts
    -0.07
    isci
    -0.07
    sburgh
    -0.07
    ransition
    -0.07
    uite
    -0.07
     pornofilm
    -0.07
    sburg
    -0.07
    uslim
    -0.07
    erras
    -0.07
    uire
    -0.07
    POSITIVE LOGITS
    icz
    0.07
    zu
    0.07
    eger
    0.07
    ook
    0.06
    İ
    0.06
     dope
    0.06
    oki
    0.06
    Ħ
    0.06
    amas
    0.06
     Vincent
    0.06
    Activations Density 0.001%

    No Known Activations