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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95531
    Prev
    Next
    INDEX
    Explanations

    common phrases and terms related to community engagement or shared experiences

    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
    agrid
    -0.07
    ache
    -0.06
    VB
    -0.06
    union
    -0.06
    fox
    -0.06
    anda
    -0.06
    esk
    -0.06
    ister
    -0.06
    ÐĴÐIJ
    -0.06
    -widgets
    -0.06
    POSITIVE LOGITS
    uhl
    0.06
    Ĭ
    0.06
    hong
    0.06
    emain
    0.06
     FU
    0.06
     заÑģÑĤ
    0.06
     Abed
    0.06
    adow
    0.06
    ädchen
    0.05
    bÃŃ
    0.05
    Activations Density 0.001%

    No Known Activations