INDEX

Explanations

episode and season references from television shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iar

-0.16

ifer

-0.16

ju

-0.16

ifier

-0.15

-0.14

vala

-0.14

esus

-0.14

IGHLIGHT

-0.14

 Hast

-0.14

POSITIVE LOGITS

tran

0.17

>(()

0.15

memberOf

0.14

tesy

0.14

sov

0.14

Ø§Ø®Øª

0.14

Ø³ØªÚ¯ÛĮ

0.13

.Assertions

0.13

ãĥĥãĤ«ãĥ¼

0.13

zman

0.13

Activations Density 0.028%

episode and season references from television shows

No Comments

No Known Activations