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. 22-LLAMASCOPE-RES-131K
    6. 4549
    Prev
    Next
    INDEX
    Explanations

    country names and their associated exclusions

    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
    ovan
    -0.08
    avr
    -0.07
     Tango
    -0.07
    ished
    -0.07
    uzzi
    -0.06
    .Accessible
    -0.06
    ignon
    -0.06
    ines
    -0.06
    eds
    -0.06
    ping
    -0.06
    POSITIVE LOGITS
    åĭ¢
    0.06
    ẻ
    0.06
     Falk
    0.06
     Guerrero
    0.06
     Saint
    0.06
     Chad
    0.06
     Lester
    0.06
    åĬ¿
    0.06
     tròn
    0.06
     Monter
    0.05
    Activations Density 0.015%

    No Known Activations