INDEX

Explanations

specific characters or symbols that may relate to identity and encoded information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

McC

-0.23

zac

-0.23

MPC

-0.22

ROC

-0.22

 McCain

-0.22

OCI

-0.22

(mContext

-0.22

McC

-0.22

Zac

-0.22

xec

-0.21

POSITIVE LOGITS

enties

0.17

 Pass

0.14

hoff

0.14

 Cliff

0.14

 Reese

0.14

unar

0.14

 Clay

0.14

arf

0.13

typings

0.13

Pass

0.13

Activations Density 0.027%

specific characters or symbols that may relate to identity and encoded information

No Comments

No Known Activations