© 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. 637
    Prev
    Next
    INDEX
    Explanations

    vertical bars and other special characters in text

    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
     zwar
    -0.08
    ories
    -0.08
    اعب
    -0.08
    cplusplus
    -0.08
    ocol
    -0.08
    .vars
    -0.08
    idences
    -0.07
    agus
    -0.07
    é£
    -0.07
    urret
    -0.07
    POSITIVE LOGITS
    ran
    0.06
     Throw
    0.06
     Mixed
    0.06
    etime
    0.05
    ators
    0.05
    amba
    0.05
    de
    0.05
     Freed
    0.05
    SPA
    0.05
    AM
    0.05
    Activations Density 0.003%

    No Known Activations