© 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. 24097
    Prev
    Next
    INDEX
    Explanations

    code snippets with file headers and memory references

    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
    çª
    -0.07
    acent
    -0.06
    aca
    -0.06
    azole
    -0.06
    gether
    -0.06
    .TO
    -0.06
    anut
    -0.06
    ComputedStyle
    -0.06
    contres
    -0.06
    esters
    -0.06
    POSITIVE LOGITS
    ories
    0.07
    iquement
    0.07
    ilian
    0.06
    orem
    0.06
     Obl
    0.06
    malink
    0.06
    149
    0.06
    .bs
    0.06
    _HIDE
    0.06
    mani
    0.06
    Activations Density 0.196%

    No Known Activations