INDEX

Explanations

various forms of the word "start" in different tenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Continue

-0.20

 Continue

-0.19

 continued

-0.19

 continue

-0.18

continued

-0.17

.dateFormat

-0.16

continue

-0.15

 Continued

-0.15

itures

-0.15

criptive

-0.14

POSITIVE LOGITS

to

0.24

 making

0.17

PFN

0.15

ÑĤÐµÐ½

0.15

 taking

0.14

ied

0.14

 Ð¿Ð¾Ð±Ð°

0.14

 XCTestCase

0.14

pace

0.14

Activations Density 0.055%

various forms of the word "start" in different tenses

No Comments

No Known Activations