INDEX

Explanations

phrases indicating exclusivity or being first in line for something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

tic

-0.18

Ãªn

-0.16

ocaust

-0.15

 carriers

-0.15

 excess

-0.14

Ã©li

-0.14

tual

-0.14

 Carrier

-0.14

ĳ¸

-0.14

ÄĻd

-0.14

POSITIVE LOGITS

Thing

0.16

ssl

0.14

chio

0.14

erti

0.13

 Thing

0.13

 Foley

0.13

apat

0.13

isclosed

0.13

scious

0.13

Activations Density 0.011%

phrases indicating exclusivity or being first in line for something

No Comments

No Known Activations