© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129245
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or communication between characters

    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
    742
    -0.09
    engan
    -0.07
    elter
    -0.07
    inders
    -0.07
    orsk
    -0.07
    анов
    -0.07
    oods
    -0.07
    دÙħ
    -0.07
    udur
    -0.06
    istrovstvÃŃ
    -0.06
    POSITIVE LOGITS
     him
    0.07
     Crack
    0.06
     Scar
    0.06
     Bench
    0.06
     them
    0.06
    ContentLoaded
    0.06
     емÑĥ
    0.06
    quisite
    0.06
    clr
    0.06
     lui
    0.06
    Activations Density 0.019%

    No Known Activations