© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27292
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters within the document

    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
    urn
    -0.07
    ekler
    -0.07
    ast
    -0.06
    иÑĢа
    -0.06
    oÄŁ
    -0.06
    FFE
    -0.06
    cbc
    -0.06
    wald
    -0.06
    ogle
    -0.06
    GINE
    -0.06
    POSITIVE LOGITS
    CrLf
    0.07
    åŃĿ
    0.07
    retch
    0.06
     hab
    0.06
    overe
    0.06
    istration
    0.06
    iets
    0.06
    umbnail
    0.06
     enc
    0.06
    eview
    0.06
    Activations Density 0.003%

    No Known Activations