© 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. 72566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or methods for change and improvement

    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
    opi
    -0.07
    nu
    -0.07
    291
    -0.06
    Readable
    -0.06
    idge
    -0.06
    pol
    -0.06
    etsy
    -0.06
     æĿ¾
    -0.06
    lej
    -0.05
    ú
    -0.05
    POSITIVE LOGITS
     ç¯
    0.08
    ëĵł
    0.07
    ken
    0.06
     вÑĭÑĢаж
    0.06
    LineStyle
    0.06
    aden
    0.06
     Lucas
    0.06
    acob
    0.06
    θÏħ
    0.06
    AXB
    0.06
    Activations Density 0.014%

    No Known Activations