© 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. 9-LLAMASCOPE-RES-131K
    11. 98277
    Prev
    Next
    INDEX
    Explanations

    terms indicating comparison or contrast between different groups or perceptions

    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
     ragaz
    -0.08
    ish
    -0.08
    aji
    -0.07
    ibri
    -0.07
    inos
    -0.06
    isman
    -0.06
    indi
    -0.06
    hattan
    -0.06
    ajar
    -0.06
    iami
    -0.06
    POSITIVE LOGITS
    icht
    0.06
    quip
    0.06
     pitch
    0.06
     Pitch
    0.06
    IW
    0.06
    ToOne
    0.06
    ectar
    0.06
    _vid
    0.06
     Richt
    0.06
    fine
    0.06
    Activations Density 0.015%

    No Known Activations