© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28970
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements related to text size

    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
    ủ
    -0.09
    rg
    -0.08
    Ãłng
    -0.07
     meiden
    -0.07
    fts
    -0.07
    feito
    -0.07
    acia
    -0.07
     NRL
    -0.07
    sing
    -0.07
    igon
    -0.07
    POSITIVE LOGITS
    -mode
    0.07
     contr
    0.06
    led
    0.06
    font
    0.06
    -sized
    0.06
     Tit
    0.06
     font
    0.06
     Gonz
    0.05
    erif
    0.05
     اÙĦÙħÙĨت
    0.05
    Activations Density 0.018%

    No Known Activations