© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97208
    Prev
    Next
    INDEX
    Explanations

    quantifiable data or statistics related to objects, events, or conditions

    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
    hang
    -0.07
    locker
    -0.07
    525
    -0.06
    AE
    -0.06
    pal
    -0.06
    aign
    -0.06
    Ñħо
    -0.06
     OPTIONAL
    -0.06
    mt
    -0.05
    252
    -0.05
    POSITIVE LOGITS
    eton
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
    ependency
    0.07
    edx
    0.07
    uling
    0.07
    isko
    0.07
    odia
    0.07
     War
    0.07
    )prepare
    0.07
    PCM
    0.07
    Activations Density 0.040%

    No Known Activations