© 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. 54491
    Prev
    Next
    INDEX
    Explanations

    elements related to events and recognition within a school context

    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
     bpp
    -0.08
     ydk
    -0.07
    upos
    -0.07
    اذ
    -0.07
    \Context
    -0.07
    URA
    -0.07
    æĶ»
    -0.07
    bris
    -0.07
    .tc
    -0.07
    ÅĤad
    -0.07
    POSITIVE LOGITS
    oger
    0.06
    è¿ľ
    0.06
    aya
    0.06
     extern
    0.06
     ìľ¤
    0.06
    flags
    0.06
     ker
    0.06
    åĪ¶ä½ľ
    0.06
    awe
    0.05
     Constitution
    0.05
    Activations Density 0.033%

    No Known Activations