INDEX

Explanations

references to structures or components related to holes or openings, particularly in a technical or anatomical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

allas

-0.16

æĤī

-0.14

.Transparent

-0.14

decorators

-0.14

colo

-0.14

 Ä°z

-0.14

Ð·ÑĮ

-0.14

æ³ķäºº

-0.14

uve

-0.13

lle

-0.13

POSITIVE LOGITS

egan

0.16

rowser

0.15

sville

0.15

igkeit

0.14

ify

0.14

eras

0.14

 dated

0.14

erus

0.14

ington

0.14

Activations Density 0.011%

references to structures or components related to holes or openings, particularly in a technical or anatomical context

No Comments

No Known Activations