INDEX

Explanations

references to geographic locations and related landmarks

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

 Wahl

-0.15

ricular

-0.15

ITERAL

-0.15

pliers

-0.14

eor

-0.14

chner

-0.14

 Biggest

-0.14

Wh

-0.14

emann

-0.14

jun

-0.14

POSITIVE LOGITS

libs

0.15

gard

0.14

ÐºÑĢÐ°ÑĹ

0.14

Ð¾Ð²ÐµÑĢ

0.14

aring

0.14

åĿĬ

0.14

èĿ

0.14

Wheel

0.14

atory

0.14

apon

0.13

Activations Density 0.025%

references to geographic locations and related landmarks

No Comments

No Known Activations