INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

gcd

-0.15

PFN

-0.15

WXYZ

-0.14

Ð¾ÐºÑģÐ¸

-0.14

æĪı

-0.14

imus

-0.14

aminer

-0.14

ocop

-0.14

oron

-0.14

.Xr

-0.14

POSITIVE LOGITS

ensure

0.26

Ensure

0.18

 Ensure

0.18

 ensure

0.18

 ensuring

0.17

ean

0.17

lag

0.17

erial

0.16

Ens

0.16

def

0.16

Activations Density 0.354%

mathematical symbols and notations

No Comments

No Known Activations