© 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. 16109
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to managing and using a clipboard interface

    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
    ...↵↵↵↵
    -0.06
    ust
    -0.06
    áºŃy
    -0.06
    leness
    -0.06
     @$_
    -0.06
     Pane
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    ãģ¶
    -0.06
     Äįe
    -0.06
    alon
    -0.06
    POSITIVE LOGITS
    onis
    0.08
    earch
    0.07
     edit
    0.06
    illin
    0.06
    ubble
    0.06
    丸
    0.06
     bulk
    0.06
     Sick
    0.06
     admin
    0.06
     integr
    0.06
    Activations Density 0.002%

    No Known Activations