© 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. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27728
    Prev
    Next
    INDEX
    Explanations

    math and prime number discussions that fail

    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/L21R
    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.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sink
    -0.07
    orian
    -0.07
    Sink
    -0.07
    arra
    -0.06
     unrelated
    -0.06
    ampp
    -0.06
    cip
    -0.06
     Leban
    -0.06
    аниÑĨ
    -0.06
    ces
    -0.06
    POSITIVE LOGITS
     partial
    0.31
     Partial
    0.26
     partially
    0.25
    Partial
    0.25
    partial
    0.23
     incomplete
    0.22
    _partial
    0.21
    .partial
    0.18
     partly
    0.15
     selective
    0.15
    Activations Density 0.266%

    No Known Activations