INDEX

Explanations

issues related to data processing errors and format compatibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÙĬÙĦØ§

-0.15

.scalablytyped

-0.14

onian

-0.14

åľĴ

-0.14

UNC

-0.14

éĥİ

-0.13

weak

-0.13

)))));↵

-0.13

 Sabha

-0.13

 knobs

-0.13

POSITIVE LOGITS

 relying

0.15

perc

0.15

sem

0.14

bomb

0.14

 funk

0.14

ligne

0.14

 havoc

0.14

kaar

0.14

 corruption

0.14

Activations Density 0.092%

issues related to data processing errors and format compatibility

No Comments

No Known Activations