© 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. 106023
    Prev
    Next
    INDEX
    Explanations

    references to media content, such as articles and stories

    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
     
    -0.08
    [
    -0.07
    ↵
    -0.06
    -
    -0.06
    essa
    -0.06
     (
    -0.06
     Es
    -0.06
     wil
    -0.06
    (
    -0.06
     debut
    -0.05
    POSITIVE LOGITS
    .MixedReality
    0.10
    kov
    0.08
    /Dk
    0.08
    æ³ģ
    0.08
     pohod
    0.08
    uggy
    0.08
     Redistributions
    0.08
    .TestCase
    0.08
    ½Ķ
    0.08
    .Generated
    0.07
    Activations Density 0.000%

    No Known Activations