INDEX

Explanations

class and function definitions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

thinkable

-0.15

ikk

-0.15

bane

-0.15

ommen

-0.15

oline

-0.15

vÄĽ

-0.15

.createComponent

-0.15

aight

-0.14

/Create

-0.14

agus

-0.14

POSITIVE LOGITS

0.16

contre

0.14

terra

0.14

Ø¬Ø¹

0.14

flate

0.14

 execution

0.13

 fortune

0.13

 bureau

0.13

Activations Density 0.148%

class and function definitions in programming code

No Comments

No Known Activations