INDEX

Explanations

locations of people or 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

anel

-0.17

abin

-0.15

uder

-0.14

rop

-0.14

agher

-0.14

emoc

-0.14

 Gone

-0.13

ones

-0.13

ihan

-0.13

isoft

-0.13

POSITIVE LOGITS

 physically

0.19

 located

0.18

thon

0.17

 headquarters

0.17

 base

0.16

 permanently

0.16

HQ

0.15

base

0.15

 headquartered

0.14

ycl

0.14

Activations Density 0.038%

locations of people or organizations

No Comments

No Known Activations