© 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. 86061
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or alternative scenarios

    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
    kiye
    -0.07
    inson
    -0.07
     знаком
    -0.06
    esson
    -0.06
     spite
    -0.06
    γκο
    -0.06
    иÑĤа
    -0.06
     Which
    -0.06
    ãĥªãĤ¢
    -0.06
     нали
    -0.06
    POSITIVE LOGITS
    andel
    0.07
    zelf
    0.06
    ncia
    0.06
    ikler
    0.06
    hind
    0.06
    ãģ®ãģłãĤįãģĨ
    0.06
    \Has
    0.06
    .IsAny
    0.06
     prelim
    0.06
     lors
    0.06
    Activations Density 0.020%

    No Known Activations