INDEX

Explanations

numeric values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

gam

-0.15

aminer

-0.15

ÃŃl

-0.15

efa

-0.14

loyd

-0.14

eless

-0.14

reu

-0.14

Sm

-0.14

ino

-0.14

arget

-0.14

POSITIVE LOGITS

flix

0.16

iyon

0.16

 depending

0.14

TestCategory

0.14

depending

0.14

iÃ©n

0.13

TestFixture

0.13

lers

0.13

ç·Ĵ

0.13

))^

0.13

Activations Density 0.062%

numeric values and measurements

No Comments

No Known Activations