INDEX

Explanations

phrases indicating perception 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 supposedly

-0.19

esian

-0.15

readcr

-0.14

 presumably

-0.14

itol

-0.14

ject

-0.14

 allegedly

-0.13

Ð¦Ðµ

-0.13

.googleapis

-0.13

ugu

-0.13

POSITIVE LOGITS

 like

0.30

ingly

0.29

lessly

0.28

 likes

0.20

 intent

0.19

 liked

0.19

 Like

0.19

Like

0.18

like

0.18

 LIKE

0.18

Activations Density 0.040%

phrases indicating perception or opinion

No Comments

No Known Activations