INDEX

Explanations

parentheses and their usage in text

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

 Consult

-0.17

plx

-0.16

PLY

-0.15

bast

-0.15

asting

-0.15

Cer

-0.14

emas

-0.14

Lag

-0.14

otle

-0.14

.Types

-0.14

POSITIVE LOGITS

aits

0.18

akens

0.17

ichen

0.15

Ø±Ø¨Ùĩ

0.15

_both

0.15

altern

0.15

 scre

0.15

asso

0.14

oons

0.14

ulla

0.14

Activations Density 0.021%

parentheses and their usage in text

No Comments

No Known Activations