INDEX

Explanations

phrases indicating repeated or consecutive occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

onio

-0.17

semb

-0.15

pty

-0.15

uch

-0.14

ÙĤØ·

-0.14

 area

-0.14

##_

-0.14

ìħ

-0.13

ikel

-0.13

POSITIVE LOGITS

mente

0.18

ingly

0.18

eon

0.18

éĤ¦

0.17

ively

0.17

aneously

0.17

ly

0.15

ÑĩÐ°ÑģÐ½Ð¾

0.14

estone

0.14

idan

0.14

Activations Density 0.021%

phrases indicating repeated or consecutive occurrences

No Comments

No Known Activations