© 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. 118355
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating importance or significance

    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
    QUENCE
    -0.08
    ABL
    -0.07
    Margins
    -0.07
    .TabIndex
    -0.07
    eries
    -0.07
    .est
    -0.07
    ptic
    -0.07
    teri
    -0.07
    ì¸ł
    -0.07
    orgot
    -0.07
    POSITIVE LOGITS
     Imp
    0.08
     imp
    0.08
     Im
    0.07
    Imp
    0.06
    .Imp
    0.06
    ure
    0.06
    ed
    0.06
    angl
    0.06
     im
    0.06
    ala
    0.06
    Activations Density 0.016%

    No Known Activations