INDEX

Explanations

phrases that encourage trying or experiencing something new

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

anker

-0.16

istik

-0.16

ëģ

-0.16

 Ð¿ÑĢÐ¸Ð¿

-0.16

ragen

-0.15

ç»ľ

-0.15

udev

-0.15

ãĥĥãĤ«ãĥ¼

-0.14

opsis

-0.14

anter

-0.14

POSITIVE LOGITS

 shot

0.52

shot

0.41

 Shot

0.40

-shot

0.36

Shot

0.36

try

0.34

 shots

0.33

_shot

0.32

 spin

0.31

 whirl

0.31

Activations Density 0.033%

phrases that encourage trying or experiencing something new

No Comments

No Known Activations