INDEX

Explanations

phrases indicating errors or exceptions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

cplusplus

-0.16

.scalablytyped

-0.15

esModule

-0.15

APO

-0.14

 sore

-0.14

 Corrections

-0.14

minus

-0.13

Exceptions

-0.13

QRST

-0.13

æĵ¦

-0.13

POSITIVE LOGITS

hyp

0.15

idal

0.14

found

0.14

immer

0.14

Fem

0.13

atel

0.13

 swims

0.13

relude

0.13

Ł

0.13

Activations Density 0.078%

phrases indicating errors or exceptions in programming code

No Comments

No Known Activations