INDEX

Explanations

occurrences of the term "analysis" and its associated phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

izen

-0.16

å¤§ä¼ļ

-0.16

lendir

-0.15

lane

-0.15

heits

-0.15

ãĥ¼ãĥ³

-0.15

Ã¼zel

-0.15

/sl

-0.15

ëĵĿ

-0.15

ality

-0.15

POSITIVE LOGITS

tical

0.21

ogue

0.21

yses

0.20

/design

0.19

(es

0.18

Ú¯Ø±Ø§ÙĨ

0.17

 paralysis

0.17

xed

0.17

conda

0.17

ÑĢÐ°ÑģÑĤ

0.16

Activations Density 0.037%

occurrences of the term "analysis" and its associated phrases

No Comments

No Known Activations