INDEX

Explanations

intensifiers that amplify the importance or quality of a statement

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ooth

-0.16

 Buen

-0.15

amilia

-0.15

cheid

-0.14

Å©i

-0.14

marker

-0.14

 incon

-0.14

hur

-0.14

urve

-0.13

ario

-0.13

POSITIVE LOGITS

 Rossi

0.15

asso

0.14

Matchers

0.14

avenous

0.14

atten

0.14

Cash

0.14

Dee

0.13

veys

0.13

aso

0.13

Activations Density 0.065%

intensifiers that amplify the importance or quality of a statement

No Comments

No Known Activations