INDEX

Explanations

references to societal norms and constructs involving identity, belonging, and the consequences of beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

MBER

-0.14

 ArgumentNullException

-0.13

 XCTAssertTrue

-0.13

 coppia

-0.13

abus

-0.13

Ø§Ø¶

-0.13

essim

-0.13

zin

-0.13

ISIBLE

-0.13

ÎķÎł

-0.13

POSITIVE LOGITS

non

1.10

Non

0.96

non

0.92

Non

0.91

NON

0.90

éĿŀ

0.86

-non

0.84

_non

0.82

.non

0.78

(non

0.77

Activations Density 0.264%

references to societal norms and constructs involving identity, belonging, and the consequences of beliefs

No Comments

No Known Activations