© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84422
    Prev
    Next
    INDEX
    Explanations

    file paths and links to JavaScript and CSS libraries

    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
    /grpc
    -0.07
    ric
    -0.07
    .libs
    -0.06
    ysa
    -0.06
    igen
    -0.06
    lector
    -0.06
    اصÙĦ
    -0.06
    rico
    -0.06
    slick
    -0.06
    nem
    -0.06
    POSITIVE LOGITS
     imp
    0.06
     Wade
    0.06
     bullet
    0.06
     Georgian
    0.06
    jeta
    0.06
    (milliseconds
    0.06
     Vance
    0.05
     Officers
    0.05
    ierz
    0.05
    idata
    0.05
    Activations Density 0.003%

    No Known Activations