© 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. 55487
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters indicating emphasis or ratings

    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
    ÑĢок
    -0.08
    aku
    -0.08
    obuf
    -0.07
    .getRandom
    -0.06
    oro
    -0.06
    orf
    -0.06
    orr
    -0.06
     Voor
    -0.06
    _EXTENSION
    -0.06
     surg
    -0.06
    POSITIVE LOGITS
    swick
    0.07
    âĨĴâĨĴ
    0.07
    egend
    0.07
    âĶ£
    0.07
    INY
    0.07
     Giang
    0.07
     grate
    0.06
     nackte
    0.06
    Scaled
    0.06
    nic
    0.06
    Activations Density 0.001%

    No Known Activations