INDEX

Explanations

code-related keywords and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Joi

-0.17

umann

-0.16

ENTS

-0.15

OTS

-0.15

phem

-0.15

SystemService

-0.15

ÙĪÙħØ§ÙĨ

-0.14

ongo

-0.14

 dumps

-0.14

.epam

-0.14

POSITIVE LOGITS

 RemoteException

0.16

 Brun

0.15

irect

0.15

oin

0.14

 mood

0.14

ii

0.14

ives

0.14

aret

0.14

è¯ĳ

0.13

uxt

0.13

Activations Density 0.311%

code-related keywords and function definitions

No Comments

No Known Activations