© 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. 86589
    Prev
    Next
    INDEX
    Explanations

    references to Java programming language imports and libraries

    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
    ear
    -0.06
    cie
    -0.06
    ney
    -0.06
    el
    -0.06
    æĸ
    -0.06
    rite
    -0.06
    emmel
    -0.06
     litt
    -0.05
    ay
    -0.05
    ’n
    -0.05
    POSITIVE LOGITS
    FilterWhere
    0.09
    _vlog
    0.09
    UpEdit
    0.08
    ocol
    0.07
    NewProp
    0.07
    IIIK
    0.07
    UrlParser
    0.07
    SplitOptions
    0.07
    .gridColumn
    0.07
    .updateDynamic
    0.07
    Activations Density 0.001%

    No Known Activations