© 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. 5169
    Prev
    Next
    INDEX
    Explanations

    content related to events and their coverage

    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
    VERTISEMENT
    -0.06
    anio
    -0.06
    mut
    -0.06
    ombie
    -0.05
    elin
    -0.05
    point
    -0.05
     alle
    -0.05
     PSA
    -0.05
    olean
    -0.05
    ETO
    -0.05
    POSITIVE LOGITS
     report
    0.10
     photos
    0.10
    photos
    0.09
     recordings
    0.09
     recording
    0.08
     biên
    0.08
     recap
    0.08
     Fotos
    0.08
     reports
    0.08
     attendee
    0.08
    Activations Density 0.186%

    No Known Activations