© 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. 27247
    Prev
    Next
    INDEX
    Explanations

    words and phrases about the ability to influence events or make a meaningful difference

    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
    ilyn
    -0.07
    nof
    -0.06
    nické
    -0.06
    uria
    -0.06
    Ñıб
    -0.06
    rego
    -0.06
     Sharp
    -0.06
    AWN
    -0.06
    assy
    -0.06
    _DIP
    -0.06
    POSITIVE LOGITS
     change
    0.17
    change
    0.15
     Change
    0.13
    Change
    0.13
    -change
    0.13
    _change
    0.13
     CHANGE
    0.12
    chang
    0.12
     chang
    0.12
    /change
    0.11
    Activations Density 0.028%

    No Known Activations