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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 75417
    Prev
    Next
    INDEX
    Explanations

    the word "como" and its variations, indicating comparisons

    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
    ses
    -0.08
    ors
    -0.08
    acades
    -0.07
    igner
    -0.07
    roe
    -0.07
     kalan
    -0.07
    opleft
    -0.07
    ·»
    -0.07
    anvas
    -0.07
    edImage
    -0.07
    POSITIVE LOGITS
     follows
    0.08
    cert
    0.08
    ž
    0.08
    ими
    0.07
    -ÑĤо
    0.07
    oci
    0.06
    pires
    0.06
    icone
    0.06
     sendo
    0.06
     Å¡to
    0.06
    Activations Density 0.009%

    No Known Activations