© 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. DeepSeek-R1-Dist-Llama-8B
    5. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23637
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express deduction, possibility, or constraint

    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
    ectl
    -0.06
    oles
    -0.06
    ooth
    -0.06
    .respond
    -0.06
    è¿·
    -0.06
    éĽĦ
    -0.06
    fu
    -0.06
    imits
    -0.06
    åŃĺäºİ
    -0.06
     вÑĸдповÑĸд
    -0.06
    POSITIVE LOGITS
     conditions
    0.08
     condition
    0.08
     rare
    0.07
    condition
    0.07
    724
    0.07
    è¦ģæ±Ĥ
    0.07
     Conditions
    0.07
     requirements
    0.06
    conditions
    0.06
     requirement
    0.06
    Activations Density 0.169%

    No Known Activations