© 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. 22-LLAMASCOPE-RES-131K
    6. 4159
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to equations and calculations

    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
     splitted
    -0.09
    plet
    -0.08
    æijĺ
    -0.07
     Flores
    -0.07
    forman
    -0.07
     Mechanics
    -0.07
     hierarchy
    -0.07
    emmel
    -0.07
     fullfile
    -0.07
    hausen
    -0.07
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
     ìĿ´ëĬĶ
    0.07
    bourne
    0.06
    621
    0.06
     derp
    0.06
    orton
    0.06
    iem
    0.06
     kì
    0.06
    ait
    0.06
     incentiv
    0.06
    Activations Density 0.025%

    No Known Activations