INDEX

Explanations

mentions of "Flash" and related terms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

plevel

-0.17

ffset

-0.16

à¸«à¸¡à¸Ķ

-0.15

hue

-0.15

Ø¬ÛĮ

-0.15

ppelin

-0.15

prs

-0.15

Unchecked

-0.14

rej

-0.14

ections

-0.14

POSITIVE LOGITS

lights

0.32

bul

0.31

backs

0.31

cards

0.30

bang

0.29

mob

0.28

 Gordon

0.27

point

0.25

light

0.25

mob

0.24

Activations Density 0.009%

mentions of "Flash" and related terms in various contexts

No Comments

No Known Activations