© 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. 75863
    Prev
    Next
    INDEX
    Explanations

    instances and discussions about the significance of language and words

    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
    ship
    -0.06
    DL
    -0.06
     reverse
    -0.06
     DL
    -0.06
     Junior
    -0.06
    brahim
    -0.06
    stead
    -0.06
     Seven
    -0.06
     Mus
    -0.06
    å±
    -0.06
    POSITIVE LOGITS
    ýt
    0.08
    mith
    0.08
    ehler
    0.07
     Morr
    0.07
    Pictures
    0.07
    SSIP
    0.06
    ξÏį
    0.06
    ÙħÙĬÙħ
    0.06
     اÙĨج
    0.06
    лаÑģÑĤи
    0.06
    Activations Density 0.021%

    No Known Activations