© 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. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23483
    Prev
    Next
    INDEX
    Explanations

    words that start with a vowel and end with "ls," or words that end with "ics" or "ks"

    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/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    -0.13
    hip
    -0.12
    oft
    -0.12
    h
    -0.11
    ets
    -0.11
    ov
    -0.10
    hat
    -0.10
    ox
    -0.10
    elf
    -0.10
    ha
    -0.10
    POSITIVE LOGITS
    ed
    0.08
    esian
    0.07
    ing
    0.07
    enna
    0.07
    nesday
    0.07
    a
    0.07
    meden
    0.07
    arian
    0.07
    rq
    0.07
    ness
    0.06
    Activations Density 0.082%

    No Known Activations