INDEX

Explanations

different tags or labels associated with content

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

abay

-0.15

 gray

-0.15

 hors

-0.15

ãĤº

-0.14

angi

-0.14

voy

-0.14

ercial

-0.14

Å¡ak

-0.14

oux

-0.14

MLE

-0.13

POSITIVE LOGITS

ged

0.17

>tag

0.15

utenberg

0.15

chr

0.15

ucker

0.14

uci

0.14

vero

0.14

ë¶

0.14

GED

0.14

Activations Density 0.008%

different tags or labels associated with content

No Comments

No Known Activations