INDEX

Explanations

punctuation marks specifically periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

é¼ĵ

-0.17

resse

-0.16

Ã¸y

-0.16

esa

-0.15

GREE

-0.15

qual

-0.14

auc

-0.14

orthand

-0.14

olini

-0.14

ÐµÐºÑĤÐ¾ÑĢÐ°

-0.14

POSITIVE LOGITS

boss

0.14

utor

0.14

 Wishlist

0.13

ìľµ

0.13

 Westbrook

0.13

/TT

0.13

_vendor

0.13

lector

0.13

eff

0.13

‘

0.12

Activations Density 0.023%

punctuation marks specifically periods

No Comments

No Known Activations