© 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. 23635
    Prev
    Next
    INDEX
    Explanations

    words that refer to history and the past or that indicate a transition in time

    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
    Intialized
    -0.06
    dbl
    -0.06
    .Automation
    -0.06
    æľĢè¿ij
    -0.06
    ãĤ¤ãĥī
    -0.06
    ÅĻez
    -0.06
    (æľĪ
    -0.06
    оби
    -0.06
    aver
    -0.06
    podob
    -0.06
    POSITIVE LOGITS
     old
    0.24
     older
    0.21
     previous
    0.21
    æŧ
    0.20
    old
    0.18
    _old
    0.17
    Previous
    0.16
    (old
    0.16
    Old
    0.15
    previous
    0.15
    Activations Density 0.052%

    No Known Activations