INDEX

Explanations

phrases related to product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.18

-0.16

onga

-0.14

Ð»Ð°ÑĢÐ°

-0.14

 downstairs

-0.14

 Irma

-0.13

¯

-0.13

 duty

-0.13

olkata

-0.13

 Slug

-0.13

POSITIVE LOGITS

iore

0.17

ALER

0.16

 Hlav

0.16

unik

0.15

acente

0.15

@nate

0.15

unks

0.14

Æ°ng

0.14

ramid

0.14

REFERRED

0.14

Activations Density 0.160%

phrases related to product features and specifications

No Comments

No Known Activations