© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29824
    Prev
    Next
    INDEX
    Explanations

    http address beginnings and apostrophes at the start of words

    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
    able
    -0.07
    /*
    -0.07
    v
    -0.07
    887
    -0.07
    id
    -0.07
    0
    -0.07
    .uk
    -0.07
    å¦Ĥä¸ĭ
    -0.06
    q
    -0.06
    ible
    -0.06
    POSITIVE LOGITS
    [email
    0.08
    ')?></
    0.08
    -addon
    0.07
     ...↵↵↵↵
    0.07
    ¶Į
    0.07
    âĢ¦↵↵↵
    0.07
    ounge
    0.07
     å¾ĴæŃ©
    0.07
    (æľ¨
    0.07
    etiyle
    0.07
    Activations Density 0.099%

    No Known Activations