INDEX

Explanations

occurrences of specific punctuation marks and their associated sequences in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.doc

-0.16

æŀ

-0.15

alice

-0.15

 comm

-0.14

ç¥

-0.14

 Minority

-0.13

 Chall

-0.13

cripcion

-0.13

iral

-0.13

âĢ¡

-0.13

POSITIVE LOGITS

¤ëĭ¤

0.16

finity

0.15

forman

0.14

rych

0.14

aidu

0.14

JKLMNOP

0.14

à¤¾à¤¯à¤¤

0.14

rippling

0.14

Ð¾ÑģÑĢÐµÐ´

0.14

InOut

0.14

Activations Density 0.362%

occurrences of specific punctuation marks and their associated sequences in the text

No Comments

No Known Activations