© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 344
    Prev
    Next
    INDEX
    Explanations

    contextual indicators of answer formatting and expectations in problem-solving situations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐĽÐŀ
    -0.06
    urb
    -0.06
    ested
    -0.06
    Ron
    -0.06
    ("$.
    -0.06
    .Hosting
    -0.06
    asing
    -0.06
     meat
    -0.05
    à¸Ľà¸£à¸°
    -0.05
    ÑĤÑĢо
    -0.05
    POSITIVE LOGITS
    andest
    0.07
    illac
    0.07
    tach
    0.06
     Flex
    0.06
    å¿Ĺ
    0.06
     flexibility
    0.06
     allowed
    0.06
    Sibling
    0.06
    OrCreate
    0.06
    orque
    0.06
    Activations Density 0.089%

    No Known Activations