© 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. 54281
    Prev
    Next
    INDEX
    Explanations

    references to former or past positions and roles

    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
    Ñģклад
    -0.08
    inel
    -0.07
    _sv
    -0.07
    ÑĤÑĥ
    -0.07
    /extensions
    -0.07
    alyzer
    -0.07
    tape
    -0.07
    ÃŃrk
    -0.07
    eros
    -0.07
     Horny
    -0.07
    POSITIVE LOGITS
     former
    0.06
    aldo
    0.06
     Former
    0.06
    767
    0.06
    lav
    0.06
     Ballard
    0.06
    attered
    0.06
    åij
    0.06
    illard
    0.06
    mc
    0.05
    Activations Density 0.006%

    No Known Activations