INDEX

Explanations

the term "bra" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.16

alus

-0.16

chal

-0.15

ortex

-0.15

ãĥ©ãĤ¹

-0.15

rÃ¡l

-0.15

istani

-0.15

shine

-0.15

orge

-0.14

yro

-0.14

POSITIVE LOGITS

zen

0.38

ided

0.37

hma

0.36

unsch

0.30

intree

0.29

iding

0.28

inte

0.28

odcast

0.28

hm

0.28

ids

0.27

Activations Density 0.006%

the term "bra" and its variations

No Comments

No Known Activations