© 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. 54900
    Prev
    Next
    INDEX
    Explanations

    terms and organizations related to academic and social science research institutions

    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
    ensa
    -0.08
    @student
    -0.07
    ogl
    -0.07
    akis
    -0.06
     asm
    -0.06
    ije
    -0.06
    ByExample
    -0.06
    nave
    -0.06
    eneg
    -0.06
    ffen
    -0.06
    POSITIVE LOGITS
    utor
    0.07
    391
    0.06
     Maison
    0.06
     Euras
    0.06
    izont
    0.06
     research
    0.06
     resc
    0.06
    _perms
    0.06
    609
    0.06
    apolis
    0.06
    Activations Density 0.013%

    No Known Activations