© 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. 80001
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions that indicate relationships and connections between 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
    stan
    -0.08
     rond
    -0.07
    Ëĺ
    -0.06
    isty
    -0.06
    ÑĢиÑģ
    -0.06
    еÑĢк
    -0.06
    ãĥ¬ãĤ¹
    -0.06
    ÑģÑĤоÑĢ
    -0.06
    عات
    -0.06
    ãĤ¯ãĥĪ
    -0.06
    POSITIVE LOGITS
     ours
    0.12
     now
    0.10
     yours
    0.09
     ahora
    0.08
    ours
    0.08
     hers
    0.07
     jetzt
    0.07
     agora
    0.07
     mine
    0.07
    now
    0.07
    Activations Density 0.024%

    No Known Activations