© 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. 130550
    Prev
    Next
    INDEX
    Explanations

    terms related to charts and charting

    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
    hood
    -0.09
    ess
    -0.07
    great
    -0.07
    داد
    -0.07
    anse
    -0.06
    _regularizer
    -0.06
    ties
    -0.06
    gle
    -0.06
    ha
    -0.06
    /stretch
    -0.06
    POSITIVE LOGITS
    reuse
    0.15
    eson
    0.09
    ismatic
    0.09
    icles
    0.08
    ifacts
    0.08
    istry
    0.08
    ingu
    0.08
    ing
    0.08
    anooga
    0.08
    ãĤ¥
    0.08
    Activations Density 0.008%

    No Known Activations