INDEX

Explanations

elements of code documentation, particularly summaries and public class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.16

oi

-0.16

 pinch

-0.16

 mind

-0.14

Nor

-0.14

InputChange

-0.14

ise

-0.14

 olmak

-0.14

 throat

-0.14

cost

-0.14

POSITIVE LOGITS

Â¤Â¤

0.18

.FC

0.16

aidu

0.16

 fisse

0.15

regor

0.15

UTERS

0.15

opak

0.15

ImageContext

0.15

bote

0.15

Activations Density 0.009%

elements of code documentation, particularly summaries and public class definitions

No Comments

No Known Activations