© 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. 125104
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and modifications

    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
    oretical
    -0.06
    Ìģ
    -0.06
    unger
    -0.06
    elsey
    -0.06
    ÑĢой
    -0.06
     Er
    -0.06
    вай
    -0.06
    aż
    -0.06
    ngle
    -0.06
    urm
    -0.06
    POSITIVE LOGITS
    лади
    0.07
    ((__
    0.07
    iqu
    0.06
     rall
    0.06
    itsu
    0.06
    èijī
    0.06
    unbind
    0.06
    .addChild
    0.06
     uintptr
    0.06
     Equip
    0.06
    Activations Density 0.040%

    No Known Activations