© 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. 71531
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operators used in expressions

    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
    /release
    -0.06
     UNUSED
    -0.06
    ede
    -0.06
    707
    -0.06
     rat
    -0.06
    eyse
    -0.06
     crack
    -0.05
     Grund
    -0.05
     áº
    -0.05
    ardi
    -0.05
    POSITIVE LOGITS
     Fate
    0.08
    avir
    0.07
    /OR
    0.07
    ritten
    0.07
    oulder
    0.06
    vla
    0.06
     anon
    0.06
    retty
    0.06
    оваÑĢи
    0.06
    ìĹŃ
    0.06
    Activations Density 0.096%

    No Known Activations