© 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. 23735
    Prev
    Next
    INDEX
    Explanations

    the letters `el` in a word.

    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
    es
    -0.16
    ed
    -0.14
    e
    -0.13
    em
    -0.10
    ess
    -0.10
    yg
    -0.10
    ex
    -0.10
    eval
    -0.10
    y
    -0.10
    ev
    -0.10
    POSITIVE LOGITS
    ts
    0.13
    icious
    0.13
    ty
    0.12
    ë¡ľ
    0.11
    led
    0.10
    ton
    0.10
    lo
    0.10
    izabeth
    0.10
    los
    0.10
    ution
    0.10
    Activations Density 0.076%

    No Known Activations