INDEX

Explanations

numerical ratios or comparisons

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

 ratio

-0.30

 Ratio

-0.26

ratio

-0.26

 ratios

-0.25

_ratio

-0.23

Ratio

-0.22

Rat

-0.21

_RATIO

-0.21

-to

-0.20

_rat

-0.18

POSITIVE LOGITS

odata

0.18

ÙĤØ·

0.18

implify

0.17

ichert

0.16

atÄ±

0.15

rian

0.15

 Brian

0.14

antium

0.14

pute

0.14

.RowStyle

0.13

Activations Density 0.140%

numerical ratios or comparisons

No Comments

No Known Activations