INDEX

Explanations

references to specific brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

owie

-0.17

 Convention

-0.16

Ð·ÑĮ

-0.15

è§Ĵ

-0.14

.Transactional

-0.14

oken

-0.14

@(

-0.14

 favour

-0.14

ÅĤug

-0.14

HWND

-0.14

POSITIVE LOGITS

Ã¢r

0.16

hoc

0.15

ngo

0.14

ÑĪÑĤ

0.14

.OP

0.14

à¤¬à¤°

0.14

abs

0.13

Ð¾ÐºÑĢÐµÐ¼Ð°

0.13

ipel

0.13

ctr

0.13

Activations Density 0.017%

references to specific brands or products

No Comments

No Known Activations