INDEX

Explanations

lines of code or comments that possibly indicate specific conditions or operations within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 jadx

-0.15

jure

-0.14

rub

-0.14

orex

-0.14

onia

-0.14

ober

-0.13

 Glow

-0.13

ayout

-0.13

las

-0.13

#End

-0.13

POSITIVE LOGITS

enger

0.16

obus

0.14

 CORS

0.14

 progressives

0.13

reste

0.13

acula

0.13

egas

0.13

 mach

0.13

ÙĦÙħÙĩ

0.13

.GroupLayout

0.13

Activations Density 0.071%

lines of code or comments that possibly indicate specific conditions or operations within a programming context

No Comments

No Known Activations