© 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. 87024
    Prev
    Next
    INDEX
    Explanations

    references to the author Jasper Fforde

    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
    족
    -0.07
    pong
    -0.07
    ¯u
    -0.07
    eous
    -0.06
    upiter
    -0.06
     Aviv
    -0.06
    'http
    -0.06
    ray
    -0.06
    endar
    -0.06
    extra
    -0.06
    POSITIVE LOGITS
    wort
    0.07
    lain
    0.07
    insula
    0.07
    adena
    0.07
    ande
    0.06
    ceae
    0.06
    oon
    0.06
    atic
    0.06
    /community
    0.06
    leta
    0.06
    Activations Density 0.008%

    No Known Activations