INDEX

Explanations

phrases indicating the setting or context of a story

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

by

-0.15

romo

-0.15

reak

-0.15

ena

-0.15

sit

-0.15

urst

-0.15

-0.14

 Proud

-0.14

POSITIVE LOGITS

lej

0.16

æĪĲ

0.16

.setDefault

0.16

 ÐľÑĸÐ½ÑĸÑģÑĤÐµÑĢ

0.15

GetMethod

0.15

lew

0.15

ulaire

0.15

itori

0.14

cka

0.14

urette

0.14

Activations Density 0.008%

phrases indicating the setting or context of a story

No Comments

No Known Activations