INDEX

Explanations

mentions of individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ess

-0.17

ANGO

-0.15

UGIN

-0.15

pearance

-0.15

YST

-0.14

Ú¯Ø§Ùĩ

-0.14

emek

-0.14

wort

-0.13

iol

-0.13

anian

-0.13

POSITIVE LOGITS

who

0.24

/groups

0.24

/entities

0.23

 whom

0.20

who

0.19

/entity

0.19

ized

0.17

itarian

0.17

ified

0.16

Who

0.16

Activations Density 0.037%

mentions of individuals and organizations

No Comments

No Known Activations