© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or categories

    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
     Moran
    -0.07
     Harm
    -0.07
    abile
    -0.06
    acement
    -0.06
    abus
    -0.06
    legate
    -0.06
    .MODE
    -0.06
    /Sub
    -0.06
    inker
    -0.06
    /alert
    -0.06
    POSITIVE LOGITS
    ster
    0.08
    vice
    0.08
    undy
    0.08
    ula
    0.07
    anic
    0.07
    sters
    0.07
    islav
    0.07
    ÛĮا
    0.06
    à¸Ľà¸£à¸°
    0.06
    ÑĥлÑıÑĢ
    0.06
    Activations Density 0.040%

    No Known Activations