© 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. 118822
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms or categories related to art and culture

    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
    à¹ij
    -0.08
    urbed
    -0.07
    .her
    -0.07
    nicos
    -0.07
    fern
    -0.07
    aldi
    -0.07
    Äł
    -0.07
    коп
    -0.07
    oris
    -0.07
    gado
    -0.07
    POSITIVE LOGITS
     variations
    0.07
     variation
    0.07
     Lair
    0.06
     Variation
    0.06
    adow
    0.06
    iez
    0.06
     embroid
    0.05
    emb
    0.05
    556
    0.05
    .SOCK
    0.05
    Activations Density 0.001%

    No Known Activations