INDEX

Explanations

superlative adjectives indicating rankings or significance

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

 Cave

-0.16

ul

-0.15

webkit

-0.15

uish

-0.15

¶

-0.14

mia

-0.14

rtl

-0.14

 Feast

-0.14

ÅŁ

-0.14

rez

-0.14

POSITIVE LOGITS

coma

0.17

ois

0.15

uestion

0.15

 Magnum

0.14

von

0.14

abel

0.14

istro

0.14

.GPIO

0.14

à¸ļà¸²à¸Ĺ

0.14

iable

0.14

Activations Density 0.055%

superlative adjectives indicating rankings or significance

No Comments

No Known Activations