INDEX

Explanations

expressions related to necessity or requirements

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

baugh

-0.17

Å¡en

-0.14

logan

-0.14

urgeon

-0.14

 Milit

-0.13

ethe

-0.13

-sample

-0.13

illing

-0.13

agic

-0.13

irl

-0.13

POSITIVE LOGITS

lessly

0.25

ÃľM

0.15

ful

0.15

istrovstvÃŃ

0.14

.Skin

0.14

Skin

0.14

AffineTransform

0.14

otine

0.14

 actionTypes

0.14

 hasNext

0.14

Activations Density 0.022%

expressions related to necessity or requirements

No Comments

No Known Activations