© 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. 86479
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Review" indicating evaluations or critiques of various subjects

    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
    x
    -0.06
     taxed
    -0.06
    æ¨
    -0.06
    ButtonModule
    -0.05
     Rid
    -0.05
    adar
    -0.05
     Edition
    -0.05
    orny
    -0.05
    ux
    -0.05
    und
    -0.05
    POSITIVE LOGITS
     ä¸
    0.08
    ivy
    0.07
    ãĥ³ãĤ¯
    0.07
    اسÙĩ
    0.07
    εÏī
    0.07
    avar
    0.07
    eyse
    0.07
    ernote
    0.07
    vak
    0.07
    ITT
    0.07
    Activations Density 0.002%

    No Known Activations