INDEX

Explanations

common articles and prepositions in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

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

 reward

-0.16

onte

-0.15

 waterfall

-0.15

ondo

-0.15

ç¸

-0.15

icie

-0.14

ymes

-0.14

olicit

-0.14

ia

-0.14

Ø®ØªÙĩ

-0.14

POSITIVE LOGITS

LS

0.15

axe

0.14

ruk

0.14

adiens

0.14

 Hancock

0.14

ELS

0.14

 Multiple

0.13

 Prepared

0.13

kud

0.13

wahl

0.13

Activations Density 0.002%

common articles and prepositions in the text

No Comments

No Known Activations