INDEX

Explanations

words that convey specific numerical quantities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ellan

-0.16

ringe

-0.15

thur

-0.15

Ø¨Ø·

-0.15

ollen

-0.15

prak

-0.14

Rated

-0.14

apl

-0.13

Gu

-0.13

adelphia

-0.13

POSITIVE LOGITS

ÅĻik

0.16

olin

0.15

ÃŃm

0.15

 setters

0.14

olib

0.14

stav

0.14

DMI

0.14

_bulk

0.14

/target

0.14

Activations Density 0.021%

words that convey specific numerical quantities or measurements

No Comments

No Known Activations