© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29986
    Prev
    Next
    INDEX
    Explanations

    phrases related to being cautious or unsure

    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
    .synthetic
    -0.06
    uitka
    -0.06
     aug
    -0.06
     counters
    -0.06
    elper
    -0.06
    unal
    -0.06
    fx
    -0.06
     realizing
    -0.06
     IG
    -0.06
    egl
    -0.05
    POSITIVE LOGITS
     safe
    0.29
     safer
    0.26
    -safe
    0.24
     safest
    0.24
    safe
    0.24
     Safe
    0.24
     safety
    0.22
    Safe
    0.22
     safely
    0.20
    _safe
    0.19
    Activations Density 0.067%

    No Known Activations