INDEX

Explanations

phrases expressing gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

mo

-0.17

hei

-0.15

 stations

-0.15

 station

-0.15

Mo

-0.15

ource

-0.14

etti

-0.14

era

-0.14

zcze

-0.14

bow

-0.14

POSITIVE LOGITS

iaux

0.18

lev

0.16

rong

0.15

Nm

0.15

ertz

0.15

CSR

0.14

à¹Ģà¸ģà¸¥

0.14

otes

0.14

bler

0.14

Activations Density 0.024%

phrases expressing gratitude or appreciation

No Comments

No Known Activations