© 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. DeepSeek-R1-Dist-Llama-8B
    5. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23133
    Prev
    Next
    INDEX
    Explanations

    the letter "T" or "t" followed by a number.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L17R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Å¡t
    -0.09
    ipo
    -0.08
    own
    -0.07
    agher
    -0.07
    Ùģ
    -0.07
    patch
    -0.07
     tender
    -0.07
    riad
    -0.07
    ime
    -0.07
    živ
    -0.07
    POSITIVE LOGITS
    ãģĬãĤĬ
    0.09
    =T
    0.08
    ushima
    0.08
    itionally
    0.08
     nhiên
    0.08
    ÑĩаÑģ
    0.08
    entieth
    0.08
     ÑĩиÑģлÑĸ
    0.08
    setter
    0.08
    othy
    0.07
    Activations Density 0.385%

    No Known Activations