INDEX

Explanations

descriptions of leading brands and prominent figures in various industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

thur

-0.19

Ã¥n

-0.16

ropolitan

-0.15

 breakdown

-0.15

-badge

-0.14

DBObject

-0.14

 INCIDENT

-0.14

ayo

-0.14

ENCH

-0.14

tas

-0.14

POSITIVE LOGITS

adir

0.15

aram

0.15

çĽĺ

0.14

arak

0.14

ero

0.14

era

0.14

ught

0.13

 diluted

0.13

áº¥t

0.13

iku

0.13

Activations Density 0.215%

descriptions of leading brands and prominent figures in various industries

No Comments

No Known Activations