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. 96170
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to visibility and display

    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
    deaux
    -0.07
     Townsend
    -0.07
    LIK
    -0.06
    647
    -0.06
    atch
    -0.06
    168
    -0.06
    aze
    -0.06
    oks
    -0.06
    angle
    -0.06
    ATCH
    -0.06
    POSITIVE LOGITS
    alien
    0.06
     ëıĮ
    0.06
     noreferrer
    0.06
     tiener
    0.06
    Trivia
    0.06
     Beverly
    0.06
    dale
    0.06
    izen
    0.06
    ìŰ
    0.06
    ìĥĪ
    0.06
    Activations Density 0.000%

    No Known Activations