© 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. 3753
    Prev
    Next
    INDEX
    Explanations

    elements of programming and technical concepts related to data structure

    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
    pcf
    -0.07
    edition
    -0.07
     Vere
    -0.07
    unday
    -0.07
    forcer
    -0.07
    trl
    -0.07
    à¥įरस
    -0.07
    åī£
    -0.07
     Gros
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
    Collision
    0.07
     collisions
    0.07
     collision
    0.07
    issen
    0.07
     vig
    0.06
    kola
    0.06
     Collision
    0.06
    mer
    0.06
    collision
    0.06
     overflow
    0.06
    Activations Density 0.004%

    No Known Activations