INDEX

Explanations

phrases indicating future actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 never

-0.23

never

-0.22

 NEVER

-0.19

 nunca

-0.18

 Never

-0.17

 Ð½Ð¸ÐºÐ¾Ð³Ð´Ð°

-0.16

already

-0.15

ral

-0.15

 already

-0.15

POSITIVE LOGITS

 need

0.24

 hell

0.24

 town

0.21

bed

0.21

need

0.21

 Hell

0.21

be

0.21

iams

0.20

 jail

0.20

hell

0.19

Activations Density 0.037%

phrases indicating future actions or intentions

No Comments

No Known Activations