© 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. 125595
    Prev
    Next
    INDEX
    Explanations

    instructional phrases related to recommendations and actions

    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
    opoulos
    -0.09
    ndx
    -0.07
    tright
    -0.07
    ابت
    -0.07
    promise
    -0.07
    lotte
    -0.07
    rám
    -0.07
    riminator
    -0.07
     :.:
    -0.07
    leyen
    -0.07
    POSITIVE LOGITS
    aves
    0.06
    uard
    0.06
    USES
    0.06
    ones
    0.06
    amp
    0.06
    rent
    0.06
    pts
    0.06
     consider
    0.06
     instant
    0.06
    net
    0.05
    Activations Density 0.008%

    No Known Activations