© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 235
    Prev
    Next
    INDEX
    Explanations

    considerations of geometric properties and relationships

    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
    omen
    -0.07
    okino
    -0.06
     deferred
    -0.06
    æĺĵ
    -0.06
    å¹ķ
    -0.06
     repeated
    -0.06
    978
    -0.06
    554
    -0.06
     Shield
    -0.06
    ids
    -0.06
    POSITIVE LOGITS
     general
    0.11
     generic
    0.09
     random
    0.08
     simply
    0.08
    _general
    0.08
    generic
    0.08
    general
    0.08
    -general
    0.07
    .general
    0.07
     Simply
    0.07
    Activations Density 0.134%

    No Known Activations