INDEX

Explanations

code snippets or syntax related to programming structures and functions

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

aga

-0.14

bear

-0.14

æĬ¼

-0.14

aul

-0.14

rade

-0.13

leep

-0.13

Ð¾Ð²Ð°ÑĢ

-0.13

oyer

-0.13

 thumb

-0.13

eyer

-0.13

POSITIVE LOGITS

æĸĹ

0.16

anj

0.15

 Marks

0.15

izr

0.14

_OPCODE

0.14

PageIndex

0.14

ı

0.14

utf

0.14

-prepend

0.14

assy

0.13

Activations Density 0.059%

code snippets or syntax related to programming structures and functions

No Comments

No Known Activations