© 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. 28828
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Maz" and its variations

    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
    .SDK
    -0.09
    ymi
    -0.08
    readcr
    -0.07
    &&&&
    -0.07
    -exclusive
    -0.07
    rieb
    -0.07
    å¹ķ
    -0.07
    exclusive
    -0.07
    undra
    -0.07
    naire
    -0.07
    POSITIVE LOGITS
    ony
    0.07
    uffer
    0.06
    AFF
    0.06
    0.06
     dis
    0.06
    vest
    0.06
     Maiden
    0.06
    аниÑĨ
    0.06
    VEST
    0.05
    ery
    0.05
    Activations Density 0.007%

    No Known Activations