INDEX

Explanations

references to academic publishing and citations

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

reau

-0.17

nave

-0.16

 Misc

-0.15

oot

-0.15

 didSet

-0.15

fid

-0.14

Outline

-0.14

ared

-0.14

 HWND

-0.14

ymm

-0.14

POSITIVE LOGITS

Oro

0.17

ucher

0.15

 Electricity

0.14

ale

0.14

iaux

0.14

inis

0.14

å¥

0.13

kaÃ§

0.13

 Virt

0.13

 pager

0.13

Activations Density 0.018%

references to academic publishing and citations

No Comments

No Known Activations