INDEX

Explanations

emotional expressions and interactions among the characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 blinked

-0.22

orro

-0.17

tir

-0.16

 seemingly

-0.15

 wink

-0.15

 Said

-0.15

 seeming

-0.15

Laugh

-0.15

æĮģ

-0.14

 blink

-0.14

POSITIVE LOGITS

 wonder

0.19

ronic

0.19

 hear

0.18

 inward

0.18

 Wonder

0.17

 mentally

0.17

Wonder

0.16

 hoped

0.16

 wondered

0.16

 shouldn

0.16

Activations Density 0.283%

emotional expressions and interactions among the characters

No Comments

No Known Activations