© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39706
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to correlation and patterns in data simulations

    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
    anova
    -0.08
    анк
    -0.08
    roje
    -0.07
    ãĤ¤ãĤ¯
    -0.07
     ÄIJo
    -0.07
    olon
    -0.07
    ahas
    -0.07
     pokoj
    -0.07
    idel
    -0.07
    íĭ
    -0.07
    POSITIVE LOGITS
     direction
    0.13
     reversal
    0.12
     opposite
    0.11
     flip
    0.11
     reversing
    0.11
     sign
    0.10
     flips
    0.10
     flipped
    0.10
     polarity
    0.10
     revers
    0.10
    Activations Density 0.240%

    No Known Activations