INDEX

Explanations

phrases that reference the availability of information or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ð¾Ð·Ð¼Ð¾Ð¶Ð½Ð¾

-0.15

zion

-0.15

aran

-0.15

uft

-0.14

uhn

-0.14

wig

-0.13

ester

-0.13

     č↵

-0.13

ÑģÐ¾Ð²

-0.13

bling

-0.13

POSITIVE LOGITS

 HERE

0.40

 here

0.40

HERE

0.32

here

0.32

 Here

0.28

 ÙĩÙĨØ§

0.26

at

0.25

_here

0.24

Here

0.22

ici

0.22

Activations Density 0.089%

phrases that reference the availability of information or sources

No Comments

No Known Activations