© 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 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. 82824
    Prev
    Next
    INDEX
    Explanations

    key concepts related to communication, media, and cultural themes

    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
    sel
    -0.07
    ázev
    -0.07
    åĩ
    -0.07
    ãĥ³ãĤ¯
    -0.06
    dez
    -0.06
    unj
    -0.06
     Quarter
    -0.06
    æŀĿ
    -0.06
    ndo
    -0.06
    PLICATE
    -0.06
    POSITIVE LOGITS
    bers
    0.07
    gorm
    0.06
    '].$
    0.06
    portun
    0.06
    izu
    0.06
    lo
    0.06
     geg
    0.06
    è¾ij
    0.06
    aker
    0.06
     tire
    0.05
    Activations Density 0.001%

    No Known Activations