INDEX

Explanations

positive adjectives and adverbs indicating improvement or enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

âĹİ

-0.18

iola

-0.15

_Tis

-0.15

ductive

-0.15

argon

-0.14

gain

-0.14

achs

-0.14

ahlen

-0.14

âĢ¦↵↵↵

-0.14

èĥĨ

-0.14

POSITIVE LOGITS

approx

0.15

 approximate

0.15

 transition

0.15

lessly

0.15

ingleton

0.15

and

0.15

edly

0.14

 exponent

0.14

ably

0.14

ap

0.14

Activations Density 0.162%

positive adjectives and adverbs indicating improvement or enhancement

No Comments

No Known Activations