© 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. 120492
    Prev
    Next
    INDEX
    Explanations

    elements of positive portrayal and representation in literature

    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
     ÑĤÑĥÑĤ
    -0.08
    .obs
    -0.07
    éĽ
    -0.07
    .mit
    -0.07
    éijij
    -0.06
    лÑİ
    -0.06
     Watt
    -0.06
    oba
    -0.06
    issent
    -0.06
    ообÑĢаз
    -0.06
    POSITIVE LOGITS
     we
    0.10
    æĪij们
    0.07
    idebar
    0.07
    ï¼ĮæĪij们
    0.06
    learn
    0.06
     Gros
    0.06
     nós
    0.06
     I
    0.06
     learn
    0.06
    pg
    0.06
    Activations Density 0.010%

    No Known Activations