INDEX

Explanations

programming-related terms and method calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eyin

-0.15

vek

-0.15

afone

-0.15

(forKey

-0.15

inand

-0.15

_deps

-0.14

ynes

-0.14

iggs

-0.14

ÐºÑĥÐ»

-0.14

POSITIVE LOGITS

/get

0.16

ChangeListener

0.16

InteractionEnabled

0.16

Ø§Ø

0.15

ParameterValue

0.15

 ì§ģìłĳ

0.15

åĢ

0.15

Ð°ÑĶ

0.14

Activations Density 0.065%

programming-related terms and method calls

No Comments

No Known Activations