© 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 EvalsExportsinterp-engineNEWAPI 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. 92364
    Prev
    Next
    INDEX
    Explanations

    words that indicate actions related to inspection and evaluation

    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
    ikip
    -0.06
    lick
    -0.06
    amp
    -0.06
    uler
    -0.06
    ìĬ¤íħĮ
    -0.06
    obraz
    -0.06
    thic
    -0.05
    atri
    -0.05
     perimeter
    -0.05
    gba
    -0.05
    POSITIVE LOGITS
     nors
    0.07
    ãĥ³ãĥIJ
    0.07
    .Slf
    0.07
    imli
    0.07
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.06
    IFO
    0.06
    esco
    0.06
     lacks
    0.06
    reo
    0.06
     hardly
    0.06
    Activations Density 0.045%

    No Known Activations