INDEX

Explanations

phrases indicating success or achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-License

-0.15

ï¸

-0.15

ampo

-0.15

iris

-0.14

exion

-0.14

/Foundation

-0.14

 RectTransform

-0.14

zac

-0.14

Vac

-0.13

POSITIVE LOGITS

gard

0.15

ãĥ«ãĥķ

0.15

arde

0.15

igon

0.14

RTC

0.14

Ä±sÄ±nÄ±n

0.14

icum

0.14

ated

0.14

0.13

uhan

0.13

Activations Density 0.004%

phrases indicating success or achievement

No Comments

No Known Activations