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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125338
    Prev
    Next
    INDEX
    Explanations

    compound words and their 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
    اتÙĩ
    -0.06
    ptions
    -0.06
    anson
    -0.06
    ات
    -0.06
    atics
    -0.06
    logy
    -0.06
     fen
    -0.06
    ımıza
    -0.06
     Blowjob
    -0.06
    IMAGE
    -0.06
    POSITIVE LOGITS
    vais
    0.07
    ward
    0.07
    füg
    0.07
    à¹Ĩ
    0.07
    lijke
    0.07
    åIJİçļĦ
    0.07
    .opensource
    0.07
    ulative
    0.07
    owy
    0.07
    akah
    0.07
    Activations Density 0.051%

    No Known Activations