© 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. 57063
    Prev
    Next
    INDEX
    Explanations

    concepts related to visibility and perception changes in art and experience

    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
    iche
    -0.07
    istra
    -0.07
    art
    -0.06
    ider
    -0.06
    âĢİ
    -0.06
    å¹ħ
    -0.06
     help
    -0.06
     unins
    -0.06
    enses
    -0.06
    help
    -0.06
    POSITIVE LOGITS
     viewers
    0.07
    usra
    0.07
    ĶåĽŀ
    0.07
     dap
    0.07
    507
    0.07
    bjerg
    0.07
    viewer
    0.06
    IRS
    0.06
     ÑģооÑĤ
    0.06
    èµĸ
    0.06
    Activations Density 0.008%

    No Known Activations