INDEX

Explanations

names of places and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ã¦r

-0.15

 COPYRIGHT

-0.15

ropri

-0.14

ÙİÙĪ

-0.14

uela

-0.14

lys

-0.14

pars

-0.14

iltr

-0.14

ield

-0.14

lys

-0.13

POSITIVE LOGITS

tan

0.25

Tan

0.23

Tan

0.23

tan

0.19

urette

0.17

ingroup

0.15

URN

0.15

Zug

0.15

dol

0.15

olan

0.15

Activations Density 0.001%

names of places and geographical locations

No Comments

No Known Activations