INDEX

Explanations

code components related to data structures and processing within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ReturnValue

-0.15

 Grat

-0.15

ifar

-0.15

uddle

-0.14

Hab

-0.14

ì±Ħ

-0.14

RunWith

-0.14

bum

-0.13

 {?>↵

-0.13

rup

-0.13

POSITIVE LOGITS

à¸²à¸į

0.15

 Bookmark

0.15

 Buchanan

0.14

illo

0.14

\param

0.14

 drag

0.13

 Baghd

0.13

ATUS

0.13

uely

0.13

lage

0.13

Activations Density 0.585%

code components related to data structures and processing within programming contexts

No Comments

No Known Activations