© 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. 106392
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to technology and medical terms

    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
    berman
    -0.07
     æ®
    -0.07
    elsing
    -0.07
    mile
    -0.07
    ekim
    -0.07
    ÑĤÑĢон
    -0.07
    ì°½
    -0.07
    mods
    -0.07
    acks
    -0.07
    omon
    -0.07
    POSITIVE LOGITS
    URY
    0.06
    ury
    0.06
    levant
    0.06
    ÑĪев
    0.06
    scape
    0.05
     incumbent
    0.05
    alles
    0.05
     labour
    0.05
    intros
    0.05
    &r
    0.05
    Activations Density 0.037%

    No Known Activations