© 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. 119310
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'i' and related vowel combinations

    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
    åµ
    -0.07
    ิà¸įà¸į
    -0.07
    #__
    -0.07
    619
    -0.07
    ANDOM
    -0.06
     Bab
    -0.06
    ossa
    -0.06
     è®
    -0.06
     bab
    -0.06
    ειο
    -0.06
    POSITIVE LOGITS
    รà¸ĵ
    0.06
     Glover
    0.06
    addtogroup
    0.06
    fiber
    0.06
    -contrib
    0.06
    Ļæ±Ł
    0.06
    cul
    0.05
     Curl
    0.05
    bsites
    0.05
    usic
    0.05
    Activations Density 0.001%

    No Known Activations