INDEX

Explanations

error-related terms, particularly those associated with exceptions in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Entered

-0.17

emer

-0.16

ĨĴ

-0.15

 <↵

-0.15

.mybatisplus

-0.14

uD

-0.14

OLON

-0.14

elage

-0.14

ActionCode

-0.14

_EMIT

-0.14

POSITIVE LOGITS

0.33

ex

0.32

 ignored

0.23

 ignore

0.21

exc

0.21

ex

0.19

exp

0.19

Ign

0.19

var

0.18

Activations Density 0.006%

error-related terms, particularly those associated with exceptions in programming

No Comments

No Known Activations