© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89651
    Prev
    Next
    INDEX
    Explanations

    instances of media content or video references

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ipsis
    -0.07
    оÑģÑĤ
    -0.06
    ostel
    -0.06
    ÑĨионной
    -0.06
     Anonymous
    -0.06
    ippo
    -0.06
    ivi
    -0.06
    κι
    -0.05
     Kostenlose
    -0.05
    Persona
    -0.05
    POSITIVE LOGITS
     details
    0.08
    enville
    0.07
    -video
    0.07
    iÄħ
    0.07
     video
    0.07
    Video
    0.07
    åĽ¾
    0.07
    etails
    0.07
    èĩ£
    0.07
    details
    0.07
    Activations Density 0.006%

    No Known Activations