INDEX

Explanations

phrases related to statistical or numerical data

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

íĺķ

-0.17

iard

-0.16

ovsky

-0.16

cation

-0.15

ovit

-0.14

htag

-0.14

aben

-0.14

ÙĤÙħ

-0.14

QUAL

-0.14

rej

-0.14

POSITIVE LOGITS

Ð½Ð°Ð½Ð½Ñı

0.16

ede

0.15

Ľi

0.15

aurus

0.14

Ã³c

0.14

 closely

0.14

YLE

0.14

uve

0.14

.wik

0.14

Activations Density 0.031%

phrases related to statistical or numerical data

No Comments

No Known Activations