INDEX

Explanations

punctuation marks and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

amm

-0.17

-0.15

ric

-0.15

vic

-0.14

ÑĨÑİ

-0.14

 Purdue

-0.14

èĬ³

-0.14

sch

-0.14

POSITIVE LOGITS

noinspection

0.18

eyen

0.17

uers

0.16

ãĥ¼ãĥŃ

0.15

abant

0.15

ctp

0.15

alloca

0.15

shint

0.14

chai

0.14

bbb

0.14

Activations Density 0.003%

punctuation marks and parentheses

No Comments

No Known Activations