INDEX

Explanations

instances of contrasting ideas and qualifiers in sentences

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

 Rubin

-0.20

chen

-0.16

egin

-0.15

orca

-0.15

rone

-0.15

ivre

-0.14

Ã¸

-0.14

ContentSize

-0.14

 atom

-0.14

nox

-0.14

POSITIVE LOGITS

alla

0.18

dio

0.16

\Base

0.14

ceae

0.14

.annot

0.14

 Ø®ÙĦÙģ

0.14

è±ª

0.14

itt

0.13

uyo

0.13

Ð»ÐµÑĢ

0.13

Activations Density 0.175%

instances of contrasting ideas and qualifiers in sentences

No Comments

No Known Activations