INDEX

Explanations

code structure related to class and interface definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ul

-0.17

 Laurel

-0.17

ul

-0.16

ctor

-0.15

uman

-0.15

arty

-0.15

orem

-0.14

ety

-0.14

ip

-0.14

Ara

-0.14

POSITIVE LOGITS

ÑĢÐ¾Ð¿

0.17

/WebAPI

0.16

ufe

0.15

UTERS

0.15

Î¿ÏħÏģÎ³

0.15

mlin

0.15

avo

0.15

IBUTE

0.14

lopedia

0.14

operate

0.14

Activations Density 0.015%

code structure related to class and interface definitions

No Comments

No Known Activations