© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    a variety of things, including changes in state ("comes", "left"), prepositional phrases ("in the"), small numbers, words related to math, and present tense verbs ending in 'ing'.

    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
    awah
    -0.07
    regor
    -0.07
     Prep
    -0.06
     boyunca
    -0.06
    oyer
    -0.06
     Preparation
    -0.06
    Ñĵ
    -0.06
     finally
    -0.06
    essim
    -0.06
    oÄį
    -0.06
    POSITIVE LOGITS
     immediate
    0.21
     immediately
    0.20
     immedi
    0.15
     Immediate
    0.14
     Immediately
    0.13
     after
    0.12
    Immediate
    0.12
     soon
    0.11
     sofort
    0.11
     post
    0.11
    Activations Density 0.018%

    No Known Activations