INDEX

Explanations

references to programming constructs and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

æ±Ĺ

-0.15

fty

-0.15

Fuse

-0.14

Neutral

-0.14

 Neutral

-0.13

alem

-0.13

.rm

-0.13

ylie

-0.13

ardown

-0.13

POSITIVE LOGITS

;↵

0.18

ì²Ń

0.16

å¤ªéĥİ

0.15

-Ð¿ÑĢÐ°Ð²

0.15

);↵

0.15

;č↵

0.14

();↵

0.14

';↵

0.14

][(

0.14

Activations Density 0.082%

references to programming constructs and syntax elements

No Comments

No Known Activations