INDEX

Explanations

programming-related terms or functions in the 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

adero

-0.17

lider

-0.15

 ?><?

-0.15

.tm

-0.15

esModule

-0.15

ngth

-0.15

vÅ¯

-0.15

upert

-0.15

clave

-0.14

etur

-0.14

POSITIVE LOGITS

 Colleg

0.14

ukan

0.14

pil

0.14

 Jordan

0.14

 incor

0.14

 expend

0.13

lica

0.13

Fri

0.13

Activations Density 0.504%

programming-related terms or functions in the code

No Comments

No Known Activations