INDEX

Explanations

punctuation marks indicating questions or dramatic pauses

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

Locator

-0.15

hti

-0.14

ÎµÎ¹Î±

-0.14

erence

-0.14

êµ¬

-0.14

 herself

-0.14

vek

-0.13

åīĽ

-0.13

fern

-0.13

anca

-0.13

POSITIVE LOGITS

0.30

we

0.28

 they

0.20

We

0.19

 none

0.18

 there

0.18

 inval

0.17

æĪĳ

0.16

our

0.16

Activations Density 0.001%

punctuation marks indicating questions or dramatic pauses

No Comments

No Known Activations