INDEX

Explanations

phrases related to events and their sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÎµÎ¹

-0.16

ÅĻÃŃ

-0.15

 schl

-0.14

rix

-0.14

esis

-0.13

bern

-0.13

ria

-0.13

aus

-0.13

èĸĦ

-0.13

ussy

-0.13

POSITIVE LOGITS

 earlier

0.26

 already

0.26

 recently

0.23

Already

0.21

 Already

0.21

already

0.20

 Earlier

0.20

 recent

0.19

Earlier

0.19

 previously

0.19

Activations Density 0.062%

phrases related to events and their sequences

No Comments

No Known Activations