INDEX

Explanations

statements of belief or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 zwar

-0.19

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

-0.17

leston

-0.17

alis

-0.16

 ÑģÐ°Ð¼Ðµ

-0.15

omik

-0.15

 Ð½ÐµÐ»ÑĮÐ·Ñı

-0.15

aliz

-0.15

ãĥĥãĤ«ãĥ¼

-0.14

already

-0.14

POSITIVE LOGITS

 ever

0.31

 really

0.23

 EVER

0.22

ever

0.21

 Ever

0.19

really

0.18

 needed

0.18

ask

0.18

 Really

0.18

Really

0.18

Activations Density 0.037%

statements of belief or opinion

No Comments

No Known Activations