INDEX

Explanations

phrases indicating something is created or structured for a specific purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eler

-0.17

 breach

-0.15

 aspect

-0.14

-UA

-0.14

asca

-0.14

lez

-0.14

 forfeiture

-0.14

ÎµÎ¹

-0.14

apphire

-0.13

 msgstr

-0.13

POSITIVE LOGITS

kv

0.17

ires

0.15

,proto

0.15

"default

0.15

ket

0.14

Ã¤Ã¤n

0.14

rette

0.14

Ð½Ð¾ÑģÑı

0.14

 perse

0.14

.setPrototypeOf

0.14

Activations Density 0.013%

phrases indicating something is created or structured for a specific purpose

No Comments

No Known Activations