INDEX

Explanations

return statements and related phrases in code or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ild

-0.14

itten

-0.14

 Incoming

-0.14

 incoming

-0.13

orsk

-0.13

bett

-0.13

abe

-0.12

 )↵↵↵↵↵↵↵↵

-0.12

mail

-0.12

miss

-0.12

POSITIVE LOGITS

 true

0.21

 instance

0.21

 promise

0.20

 void

0.20

true

0.19

 always

0.19

 result

0.19

 Promise

0.19

.promise

0.19

 Returns

0.18

Activations Density 0.046%

return statements and related phrases in code or documentation

No Comments

No Known Activations