INDEX

Explanations

educational levels and grade classifications

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

ãĥªãĥ¼ãĤº

-0.15

wicklung

-0.15

MMdd

-0.14

acades

-0.14

dec

-0.14

ĵn

-0.14

combe

-0.13

å¹¹

-0.13

mscorlib

-0.13

âĨĵ

-0.13

POSITIVE LOGITS

0.26

Gray

0.17

-col

0.17

-grade

0.17

-post

0.17

 Gray

0.16

gne

0.16

gray

0.15

dg

0.15

Activations Density 0.007%

educational levels and grade classifications

No Comments

No Known Activations