INDEX

Explanations

terms related to mathematical equations and scientific analysis

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intox

-0.15

orer

-0.15

ASIC

-0.15

illas

-0.14

utton

-0.14

usta

-0.14

cale

-0.14

huz

-0.14

eid

-0.13

orre

-0.13

POSITIVE LOGITS

kas

0.17

0.15

 ideal

0.15

tre

0.15

 approx

0.15

 TMPro

0.14

lam

0.14

 Disclaimer

0.14

 model

0.14

 synthetic

0.14

Activations Density 0.119%

terms related to mathematical equations and scientific analysis

No Comments

No Known Activations