© 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. 118666
    Prev
    Next
    INDEX
    Explanations

    concepts related to hope and desire

    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
     syn
    -0.06
    645
    -0.06
    511
    -0.06
     contradictions
    -0.06
    aska
    -0.06
    word
    -0.06
    _study
    -0.06
     Tone
    -0.06
    isphere
    -0.06
     perceptions
    -0.06
    POSITIVE LOGITS
     Minimal
    0.08
     redes
    0.07
    reon
    0.07
    Minimal
    0.07
     Straw
    0.07
    Ñĵ
    0.07
    ukkan
    0.07
     commitments
    0.07
    ordion
    0.07
    opup
    0.06
    Activations Density 0.093%

    No Known Activations