© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29753
    Prev
    Next
    INDEX
    Explanations

    words that involve defense or justification

    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
    TRL
    -0.08
    936
    -0.06
    .rcParams
    -0.06
    yw
    -0.06
    593
    -0.06
    APA
    -0.06
    ież
    -0.06
    alama
    -0.06
    OTE
    -0.06
    برد
    -0.06
    POSITIVE LOGITS
     why
    0.10
     claims
    0.10
     claim
    0.09
     claimed
    0.08
    ably
    0.08
     existence
    0.08
    ivet
    0.07
    Why
    0.07
    why
    0.07
     Claim
    0.07
    Activations Density 0.019%

    No Known Activations