© 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. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27468
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning, conditional statements, and conclusions "need", "would", "they"

    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
    faction
    -0.07
    .scalablytyped
    -0.07
    eyin
    -0.07
    742
    -0.07
    ilinear
    -0.06
    asse
    -0.06
    _GRANTED
    -0.06
    ulos
    -0.06
    oles
    -0.06
    uckle
    -0.06
    POSITIVE LOGITS
     must
    0.20
     Must
    0.19
    å¿ħé¡»
    0.18
    Must
    0.17
    must
    0.17
     MUST
    0.14
     needs
    0.14
     å¿ħ
    0.13
     requires
    0.12
     phải
    0.11
    Activations Density 0.082%

    No Known Activations