© 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 EvalsExportsAPI 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. 88599
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions related to actions or ideas

    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
    agle
    -0.07
    agh
    -0.07
    ecn
    -0.07
    ómo
    -0.07
    аки
    -0.07
    á»IJ
    -0.06
    idis
    -0.06
    anst
    -0.06
     Pru
    -0.06
    beit
    -0.06
    POSITIVE LOGITS
    _Lean
    0.06
    .GroupLayout
    0.06
    ermen
    0.06
     familiar
    0.06
    .UIManager
    0.06
     Solid
    0.06
    GuidId
    0.06
    704
    0.06
     strongly
    0.06
     Fam
    0.06
    Activations Density 0.009%

    No Known Activations