INDEX

Explanations

names of authors or researchers in mathematical literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

raq

-0.17

uld

-0.17

ooks

-0.15

Ð¾ÑĤÑĮ

-0.15

Ã¡v

-0.15

lesen

-0.14

Ã¼rnberg

-0.14

PCA

-0.14

andro

-0.14

RL

-0.14

POSITIVE LOGITS

 proved

0.20

 prove

0.18

MR

0.16

 proving

0.15

 proves

0.15

ductive

0.14

 repro

0.14

.rpm

0.14

Dia

0.14

MR

0.14

Activations Density 0.062%

names of authors or researchers in mathematical literature

No Comments

No Known Activations