INDEX

Explanations

equality and comparison operators in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

indsight

-0.17

åĪ¥

-0.15

strup

-0.15

zym

-0.14

vider

-0.14

ibil

-0.14

atti

-0.14

icals

-0.14

agini

-0.14

rost

-0.14

POSITIVE LOGITS

/=

0.16

ÂłÐĶ

0.15

ÑĤÑĢÐ¾

0.14

ingly

0.14

 nhau

0.14

vous

0.14

 Merkez

0.13

ÂłÐ£

0.13

 Mara

0.13

ahlen

0.13

Activations Density 0.072%

equality and comparison operators in code

No Comments

No Known Activations