INDEX

Explanations

terms related to criticism of societal norms and behaviors, particularly focusing on perceived stupidity and hypocrisy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

elper

-0.16

ì§¸

-0.16

_Reset

-0.14

orus

-0.14

 Kind

-0.14

ãĥĬãĥ¼

-0.14

POSITIVE LOGITS

Ð¾ÑģÑĤÑĮ

0.16

.Path

0.15

GED

0.15

 Ders

0.14

nat

0.14

reira

0.14

EGA

0.14

 CONTRIBUTORS

0.14

Ð¾ÑģÑĤÐ¸

0.14

ul

0.14

Activations Density 0.416%

terms related to criticism of societal norms and behaviors, particularly focusing on perceived stupidity and hypocrisy

No Comments

No Known Activations