INDEX

Explanations

statements of denial or claims of innocence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ilk

-0.15

 Ð¢Ð¸

-0.14

.Foundation

-0.14

 ê·¼

-0.14

erus

-0.14

ckt

-0.14

 sent

-0.14

wdx

-0.13

ller

-0.13

áº¥n

-0.13

POSITIVE LOGITS

 Maiden

0.18

Ã¥de

0.15

emies

0.15

ÙĪØ«

0.15

 ÑģÐ²Ð¾Ðµ

0.14

owers

0.14

opsy

0.14

nie

0.14

zeug

0.14

(?:

0.14

Activations Density 0.004%

statements of denial or claims of innocence

No Comments

No Known Activations