© 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. 72349
    Prev
    Next
    INDEX
    Explanations

    elements related to television shows and their production aspects

    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
    imenti
    -0.07
    .scalablytyped
    -0.07
    ocaly
    -0.06
     æļ
    -0.06
    iry
    -0.06
    θÏħ
    -0.06
    éŁ¿
    -0.06
    inae
    -0.06
    éĺħ读次æķ°
    -0.06
    agli
    -0.06
    POSITIVE LOGITS
     segments
    0.10
     Segment
    0.08
    segments
    0.08
     Seg
    0.08
     segment
    0.08
     guests
    0.08
    SEG
    0.08
    segment
    0.07
     audience
    0.07
     callers
    0.07
    Activations Density 0.016%

    No Known Activations