INDEX

Explanations

elements related to programming or coding concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

illez

-0.15

à¹Ĥà¸ŀ

-0.15

htdocs

-0.15

 Barrel

-0.15

zeitig

-0.15

ãĥªãĥ¼

-0.15

à¹Ĥà¸¡

-0.15

 Weiss

-0.15

loe

-0.14

Ã¶tt

-0.14

POSITIVE LOGITS

 reverse

0.29

éĢĨ

0.27

reverse

0.27

 backwards

0.26

_reverse

0.25

 backward

0.25

 reversed

0.24

 Reverse

0.24

[::-

0.23

åĢĴ

0.23

Activations Density 0.170%

elements related to programming or coding concepts

No Comments

No Known Activations