© 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. 123781
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "self" or "itself."

    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
    lo
    -0.06
    åĪ°çļĦ
    -0.06
    afs
    -0.06
    jav
    -0.06
     Vaults
    -0.06
    lok
    -0.06
     Tate
    -0.06
     gek
    -0.06
    ond
    -0.05
     Vu
    -0.05
    POSITIVE LOGITS
     itself
    0.10
    atform
    0.08
    LLU
    0.08
    enis
    0.07
    pline
    0.07
    анÑģи
    0.07
    cÃŃch
    0.07
    pio
    0.07
    zelf
    0.07
     à¹Ĩ
    0.07
    Activations Density 0.009%

    No Known Activations