© 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. 9-LLAMASCOPE-RES-131K
    11. 95569
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases indicating uncertainty or variability

    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
    enburg
    -0.07
    amp
    -0.07
    _PROTOCOL
    -0.06
    inium
    -0.06
    kov
    -0.06
    egin
    -0.06
    wner
    -0.06
    едж
    -0.06
    enberg
    -0.06
    اتÛĮ
    -0.06
    POSITIVE LOGITS
    epam
    0.07
    agrams
    0.06
     Grim
    0.06
     >",
    0.06
    getManager
    0.06
    rends
    0.06
    agram
    0.06
    __/
    0.06
    ulk
    0.06
    )NULL
    0.06
    Activations Density 0.027%

    No Known Activations