INDEX

Explanations

punctuation marks, particularly periods and exclamation points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

arsing

-0.15

ccoli

-0.14

bob

-0.14

/loose

-0.14

$$$$

-0.14

éŀ

-0.14

"profile

-0.14

-0.13

actionDate

-0.13

 Grim

-0.13

POSITIVE LOGITS

oden

0.15

hatt

0.15

 rein

0.14

chest

0.14

osu

0.14

 chron

0.14

Gow

0.14

ailable

0.14

_Height

0.14

Activations Density 0.002%

punctuation marks, particularly periods and exclamation points

No Comments

No Known Activations