INDEX

Explanations

instances of gratitude or appreciation expressed in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

spl

-0.15

Ð»ÑĥÐ³

-0.14

utas

-0.14

 Ð·Ð°Ð²Ð¸

-0.14

ICLES

-0.14

istes

-0.13

ATIC

-0.13

TION

-0.13

isode

-0.13

ottes

-0.13

POSITIVE LOGITS

it

0.19

 there

0.18

anky

0.17

we

0.16

 hence

0.15

 this

0.15

 they

0.15

it

0.14

 Carly

0.14

there

0.14

Activations Density 0.245%

instances of gratitude or appreciation expressed in the text

No Comments

No Known Activations