© 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. 5-LLAMASCOPE-RES-131K
    11. 126926
    Prev
    Next
    INDEX
    Explanations

    words that imply degrees of intensity or quality

    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
    imbus
    -0.06
    оÑĢаз
    -0.06
    imax
    -0.06
     Bates
    -0.06
    esk
    -0.06
     than
    -0.06
    御
    -0.06
    thal
    -0.05
     prec
    -0.05
    adesh
    -0.05
    POSITIVE LOGITS
     ãĥĶ
    0.07
    brit
    0.07
    AZY
    0.07
    머ëĭĪ
    0.07
     pathMatch
    0.07
    384
    0.07
    ///<
    0.07
    NotAllowed
    0.06
    ãĥĸãĥª
    0.06
    Äįer
    0.06
    Activations Density 0.103%

    No Known Activations