© 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. 27000
    Prev
    Next
    INDEX
    Explanations

    the word 'which' followed by a form of the verb 'to be' or the preposition 'in'

    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
    llx
    -0.07
    het
    -0.07
    شت
    -0.06
    ibur
    -0.06
    pit
    -0.06
     Bucc
    -0.06
    iny
    -0.06
     pulumi
    -0.06
    /resources
    -0.06
    ÙģÛĮ
    -0.06
    POSITIVE LOGITS
     turn
    0.44
     Turn
    0.32
    turn
    0.29
    -turn
    0.28
     turns
    0.28
    Turn
    0.27
     TURN
    0.26
    _turn
    0.24
    TURN
    0.23
    .turn
    0.23
    Activations Density 0.031%

    No Known Activations