INDEX

Explanations

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

inja

-0.17

anders

-0.17

 indeed

-0.17

ichen

-0.16

 therefore

-0.15

ainter

-0.15

iland

-0.15

rvine

-0.15

gew

-0.14

çī§

-0.14

POSITIVE LOGITS

 à¹Ĩ

0.15

à¥ĩà¤¹à¤°

0.15

 ÄĮesko

0.14

Ð»ÐºÐ¸

0.14

lik

0.14

.scalablytyped

0.14

ked

0.14

abcdefghijklmnop

0.14

StandardItem

0.14

.dk

0.14

Activations Density 0.018%

punctuation marks, particularly commas

No Comments

No Known Activations