INDEX

Explanations

references to specific products or models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 frontal

-0.17

Bu

-0.15

Fi

-0.15

istan

-0.14

ret

-0.14

 earlier

-0.14

roke

-0.14

bu

-0.14

rg

-0.14

POSITIVE LOGITS

.RunWith

0.17

PEC

0.17

ehr

0.16

hoc

0.15

.WinForms

0.15

lÃŃn

0.15

æµ©

0.15

Dll

0.14

ACKET

0.14

 TaÅŁ

0.14

Activations Density 0.073%

references to specific products or models

No Comments

No Known Activations