INDEX

Explanations

technical terms and components related to programming and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ecies

-0.17

bine

-0.17

osa

-0.15

yak

-0.14

opic

-0.14

à¸±à¸ģà¸©

-0.14

uta

-0.14

.truth

-0.14

jÃł

-0.13

.Reporting

-0.13

POSITIVE LOGITS

prox

0.17

 burg

0.14

ocab

0.14

Ð»Ð¸Ð²

0.14

ÙĨØ§ÙħÙĩ

0.13

icer

0.13

 Benefit

0.13

Wel

0.13

 Harmon

0.12

_prefs

0.12

Activations Density 0.046%

technical terms and components related to programming and event handling

No Comments

No Known Activations