© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2709
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss correctness and variations based on conventions or contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     app
    -0.07
    1
    -0.07
    ...
    -0.07
     concepts
    -0.07
     Concepts
    -0.07
     (
    -0.07
     |
    -0.07
    ..
    -0.07
    ↵
    -0.07
    âĢ¦
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.09
     preference
    0.08
    _preference
    0.08
     preferences
    0.08
     Preference
    0.07
    çĮľ
    0.07
    preferences
    0.07
    ÑĤаб
    0.07
    (çģ«
    0.07
    ê»ĺ
    0.07
    Activations Density 0.039%

    No Known Activations