© 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. 59560
    Prev
    Next
    INDEX
    Explanations

    references to animals, particularly mammals

    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
    ór
    -0.08
    omo
    -0.08
    619
    -0.08
    raq
    -0.07
    ió
    -0.07
    elay
    -0.07
    zos
    -0.07
    ersh
    -0.07
    omers
    -0.07
    hani
    -0.07
    POSITIVE LOGITS
    /she
    0.09
    -shaped
    0.08
    eyed
    0.07
    kin
    0.07
    /her
    0.07
    /cat
    0.07
    -headed
    0.07
     catcher
    0.07
    thern
    0.07
     breeding
    0.06
    Activations Density 0.064%

    No Known Activations