© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28943
    Prev
    Next
    INDEX
    Explanations

    issues related to software errors and updates

    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
    aign
    -0.07
     pant
    -0.06
    çķª
    -0.06
     Dio
    -0.06
     getCode
    -0.06
    outu
    -0.06
    Outline
    -0.06
    amax
    -0.06
    oman
    -0.06
     Human
    -0.06
    POSITIVE LOGITS
     cluster
    0.07
    adoop
    0.07
    ureka
    0.07
     Apache
    0.07
     clusters
    0.07
     Palo
    0.07
    /apache
    0.07
    .cluster
    0.07
    .apache
    0.07
    cluster
    0.07
    Activations Density 0.008%

    No Known Activations