© 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. 17-LLAMASCOPE-RES-131K
    11. 16554
    Prev
    Next
    INDEX
    Explanations

    numerical values along with related symbols

    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
    ³
    -0.07
    onia
    -0.07
    ado
    -0.07
    icios
    -0.06
    ship
    -0.06
    iqu
    -0.06
    lymp
    -0.06
    мÑĭ
    -0.06
     undef
    -0.06
    ners
    -0.06
    POSITIVE LOGITS
    éĢģæĸĻçĦ¡æĸĻ
    0.08
    istrovstvÃŃ
    0.07
     Ekon
    0.07
    ãĥ³ãĤ°ãĥ«
    0.07
    jte
    0.07
    TriState
    0.07
    «ĺ
    0.07
    Ïģκε
    0.07
    BackingField
    0.07
    AILABLE
    0.07
    Activations Density 0.087%

    No Known Activations