© 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. 74959
    Prev
    Next
    INDEX
    Explanations

    expressions related to making decisions or choices

    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
     track
    -0.06
     radi
    -0.06
     butt
    -0.06
    ãĥ¼ãĥ
    -0.06
    strtolower
    -0.05
    ç¥ŀ
    -0.05
     acronym
    -0.05
    ÅĻ
    -0.05
    ly
    -0.05
    osc
    -0.05
    POSITIVE LOGITS
    etine
    0.09
    éĺ¶
    0.07
    elper
    0.07
    GenerationStrategy
    0.07
     scand
    0.07
    icontrol
    0.07
    andes
    0.07
    racak
    0.07
    ediator
    0.07
    Ao
    0.07
    Activations Density 0.001%

    No Known Activations