INDEX

Explanations

event details and organization information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

¥

-0.20

/umd

-0.16

lando

-0.15

 vero

-0.15

xford

-0.14

rels

-0.14

unge

-0.14

Ø®ØµØµ

-0.14

vey

-0.14

ipa

-0.13

POSITIVE LOGITS

iku

0.14

Range

0.14

-LAST

0.14

tas

0.14

_nested

0.14

 Range

0.14

assage

0.14

 Cruc

0.14

 RANGE

0.14

outu

0.13

Activations Density 0.149%

event details and organization information

No Comments

No Known Activations