INDEX

Explanations

proper nouns, especially names related to individuals and brands

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

erer

-0.14

á»ī

-0.14

ÐºÐ¾Ð²Ð¾Ð¹

-0.14

culus

-0.14

ERO

-0.14

kees

-0.14

elson

-0.14

 tÃ¡c

-0.14

vious

-0.13

uchs

-0.13

POSITIVE LOGITS

VERN

0.22

/fwlink

0.18

busters

0.17

ÅĽcie

0.17

thic

0.17

zilla

0.17

ÅĤÄħ

0.15

inge

0.15

Äįin

0.15

ekli

0.15

Activations Density 0.036%

proper nouns, especially names related to individuals and brands

No Comments

No Known Activations