INDEX

Explanations

references to various types of operations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

olit

-0.15

pitch

-0.14

ongs

-0.14

 Bilim

-0.14

 scape

-0.14

porto

-0.14

 æ±

-0.14

jit

-0.14

antt

-0.14

ea

-0.13

POSITIVE LOGITS

entric

0.18

innacle

0.17

ally

0.16

/action

0.15

alley

0.15

avec

0.15

avi

0.15

.addAction

0.14

urve

0.14

adal

0.14

Activations Density 0.022%

references to various types of operations in programming contexts

No Comments

No Known Activations