INDEX

Explanations

time indicators and numerical data, particularly around timestamps and financial figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.15

 slowly

-0.14

res

-0.14

sher

-0.14

wr

-0.13

 hyper

-0.13

 latter

-0.13

uario

-0.13

yk

-0.13

iki

-0.13

POSITIVE LOGITS

eyim

0.19

 itemprop

0.17

Ä©a

0.16

 HÃ²a

0.14

omnia

0.14

.GroupLayout

0.14

ë¥

0.13

.github

0.13

.scalablytyped

0.13

activex

0.13

Activations Density 0.137%

time indicators and numerical data, particularly around timestamps and financial figures

No Comments

No Known Activations