© 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. 29363
    Prev
    Next
    INDEX
    Explanations

    references to geometric objects, especially lines and points and when those objects "go" somewhere

    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
    ires
    -0.06
    ewn
    -0.06
    _CM
    -0.06
    -toggler
    -0.06
    ¦æĥħ
    -0.06
    ноÑĩ
    -0.06
    erif
    -0.06
    881
    -0.06
    volt
    -0.05
    orWhere
    -0.05
    POSITIVE LOGITS
     hitting
    0.11
     intersects
    0.10
     ending
    0.09
     hit
    0.09
     hits
    0.09
     intersect
    0.09
     meeting
    0.09
     meets
    0.08
     landing
    0.08
     intercept
    0.08
    Activations Density 0.163%

    No Known Activations