INDEX

Explanations

phrases featuring elements of cause and effect or structural relationships in writing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eniable

-0.21

imoto

-0.14

êµ´

-0.14

ÐºÐ¾Ð²Ð¾

-0.14

itionally

-0.13

ä¼ı

-0.13

å®ľ

-0.13

 ifndef

-0.13

Ð»Ð¸Ð½Ð¸

-0.13

aturas

-0.13

POSITIVE LOGITS

ugu

0.15

Jeg

0.14

ag

0.14

_exempt

0.14

 Ãĸr

0.13

Ð²Ð°Ð½Ð¾

0.13

ILog

0.13

IOC

0.13

ug

0.13

Ã¤t

0.13

Activations Density 0.636%

phrases featuring elements of cause and effect or structural relationships in writing

No Comments

No Known Activations