© 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. 15-LLAMASCOPE-RES-131K
    11. 26461
    Prev
    Next
    INDEX
    Explanations

    past participle verbs and words related to publication and print

    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
    ioni
    -0.07
    ạ
    -0.07
    CompleteListener
    -0.07
    ibold
    -0.07
    soles
    -0.07
    edo
    -0.06
    ngen
    -0.06
    edl
    -0.06
    avicon
    -0.06
    etz
    -0.06
    POSITIVE LOGITS
    áÄį
    0.06
    keit
    0.06
    irket
    0.06
    bakan
    0.06
     Carey
    0.06
     Eaton
    0.06
     byteArray
    0.06
    OCUS
    0.06
    .Dial
    0.06
    ÏĦη
    0.06
    Activations Density 0.003%

    No Known Activations