INDEX

Explanations

references to journal volume and issue numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Sche

-0.16

ÏĦÎµÏģ

-0.13

Lis

-0.13

dete

-0.13

xba

-0.13

);;↵

-0.13

arsers

-0.13

endi

-0.12

 ;;↵

-0.12

 Mant

-0.12

POSITIVE LOGITS

0.30

kir

0.17

tip

0.17

toolbox

0.16

.ï¼ı

0.16

.?

0.16

.$

0.15

.]

0.15

.%

0.15

Activations Density 0.008%

references to journal volume and issue numbers

No Comments

No Known Activations