INDEX

Explanations

references to historical events and their associated figures

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

ensa

-0.17

cala

-0.16

vailability

-0.16

nar

-0.15

zc

-0.15

Lod

-0.15

 strm

-0.14

ÙĬØ¨

-0.14

iges

-0.14

ilit

-0.14

POSITIVE LOGITS

 band

0.17

uisine

0.16

 Revolution

0.15

HQ

0.15

bol

0.15

ftype

0.15

Æ°u

0.14

agination

0.14

hq

0.14

ħ

0.14

Activations Density 0.224%

references to historical events and their associated figures

No Comments

No Known Activations