INDEX

Explanations

references to notable films and stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÙĦÛĮØ³ÛĮ

-0.16

foundland

-0.15

edic

-0.15

ÑģÐ°Ð¼

-0.15

ettel

-0.15

 prank

-0.15

.ss

-0.14

Ð¡Ðł

-0.14

ä»

-0.14

ilon

-0.14

POSITIVE LOGITS

ren

0.16

assis

0.15

zoom

0.14

ë²Ķ

0.14

 diver

0.14

locker

0.14

bst

0.14

Hor

0.14

 study

0.14

alary

0.13

Activations Density 0.172%

references to notable films and stories

No Comments

No Known Activations