© 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. 78079
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to programs and initiatives

    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
    efs
    -0.07
    Homepage
    -0.07
    reich
    -0.07
    byss
    -0.07
    éĺħ读次æķ°
    -0.07
     trÃŃ
    -0.06
    bjerg
    -0.06
    ãĤ¯ãĥ©ãĥĸ
    -0.06
    .myapplication
    -0.06
    achuset
    -0.06
    POSITIVE LOGITS
    isel
    0.06
    illion
    0.06
    alink
    0.06
    nev
    0.06
    vre
    0.06
    itia
    0.06
    ulate
    0.06
     simply
    0.05
     harass
    0.05
     /**<
    0.05
    Activations Density 0.041%

    No Known Activations