© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 357
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results

    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
    abil
    -0.06
    esian
    -0.06
    afort
    -0.06
    NEY
    -0.06
    azard
    -0.06
    chten
    -0.06
    eson
    -0.06
    éri
    -0.06
    aper
    -0.06
    žil
    -0.06
    POSITIVE LOGITS
     Moran
    0.06
    ivas
    0.06
     +
    0.06
    merc
    0.06
    ayd
    0.06
    embre
    0.06
    legg
    0.06
     Struct
    0.06
    ipp
    0.06
    Substring
    0.05
    Activations Density 0.149%

    No Known Activations