Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3617
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their associated class attributes

    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
    andom
    -0.07
    uye
    -0.07
    igon
    -0.06
    oldt
    -0.06
    uten
    -0.06
    emo
    -0.06
    cdn
    -0.06
    erd
    -0.06
    owl
    -0.06
    reta
    -0.06
    POSITIVE LOGITS
     valign
    0.07
    /loader
    0.07
     vin
    0.07
    lamaz
    0.07
     HÃłng
    0.06
    QPushButton
    0.06
     thụ
    0.06
    /sbin
    0.06
     LENG
    0.06
     atmos
    0.06
    Activations Density 0.006%

    No Known Activations