INDEX

Explanations

punctuation marks signaling sentence boundaries

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

aeda

-0.18

roys

-0.17

hibit

-0.15

 Ð¸Ð¼Ñĥ

-0.15

ounc

-0.15

bler

-0.15

jak

-0.15

inki

-0.14

iyi

-0.14

à¸¥à¸²à¸¢

-0.14

POSITIVE LOGITS

0.15

ILLISECONDS

0.15

0.14

0.13

ä¹Ļ

0.13

 CONSEQUENTIAL

0.13

iw

0.13

sur

0.12

 vidÃ©os

0.12

Activations Density 0.036%

punctuation marks signaling sentence boundaries

No Comments

No Known Activations