© 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. 77089
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or surprise

    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
    orsi
    -0.07
    mtree
    -0.07
    uely
    -0.07
    endale
    -0.07
    обÑĢаÐ
    -0.07
    à¥Įड
    -0.07
    sync
    -0.06
    uman
    -0.06
    type
    -0.06
    loub
    -0.06
    POSITIVE LOGITS
     somew
    0.13
     else
    0.09
    ness
    0.08
     somehow
    0.08
     magically
    0.07
    NESS
    0.07
    _else
    0.07
    LLL
    0.07
    onen
    0.07
     managing
    0.07
    Activations Density 0.005%

    No Known Activations