INDEX

Explanations

commas in lists or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

abis

-0.17

adera

-0.16

å¡Ķ

-0.15

.rl

-0.14

egative

-0.14

å·®

-0.14

pcs

-0.14

 componentWillUnmount

-0.14

ulling

-0.14

ayo

-0.14

POSITIVE LOGITS

 Bookmark

0.16

rogen

0.15

ocale

0.15

HAM

0.15

isha

0.15

Mun

0.15

ovich

0.14

Operators

0.14

vens

0.14

Activations Density 0.021%

commas in lists or phrases

No Comments

No Known Activations