© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41002
    Prev
    Next
    INDEX
    Explanations

    instances of spatial or contextual positioning

    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
     æ¨
    -0.07
    imes
    -0.07
    illa
    -0.07
     DNA
    -0.07
    ellites
    -0.07
     Orta
    -0.07
    DNA
    -0.06
    imal
    -0.06
    iliz
    -0.06
    ?url
    -0.06
    POSITIVE LOGITS
     Coff
    0.07
    bling
    0.07
    affer
    0.06
    empor
    0.06
    oeff
    0.06
    uid
    0.06
     coff
    0.06
     net
    0.06
    aud
    0.06
    ICO
    0.06
    Activations Density 0.000%

    No Known Activations