© 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. 15-LLAMASCOPE-RES-131K
    11. 103748
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to events

    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
    istrovstvÃŃ
    -0.07
    abar
    -0.07
    олж
    -0.07
    reso
    -0.06
    еÑĪ
    -0.06
     fas
    -0.06
    ruba
    -0.06
    dej
    -0.06
    uzu
    -0.06
     Summers
    -0.06
    POSITIVE LOGITS
    edis
    0.07
    305
    0.06
     Chapman
    0.06
    edly
    0.06
    mgr
    0.06
     McK
    0.06
    ervas
    0.06
    onas
    0.06
    825
    0.06
    uentes
    0.05
    Activations Density 0.001%

    No Known Activations