INDEX

Explanations

code-related terms and actions, particularly those involving object construction 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÐµÐ¸

-0.16

.tc

-0.15

uC

-0.15

ogan

-0.14

fa

-0.14

ibraltar

-0.14

 ç·¨

-0.14

erno

-0.14

?v

-0.14

oldem

-0.14

POSITIVE LOGITS

croft

0.15

0.13

Gro

0.13

 pulumi

0.13

_flg

0.13

 Falk

0.13

ig

0.13

Ø§Ø¶

0.13

apid

0.13

 conc

0.13

Activations Density 0.003%

code-related terms and actions, particularly those involving object construction and interface definitions

No Comments

No Known Activations