INDEX

Explanations

elements of exaggerated storytelling or melodrama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

buz

-0.16

eya

-0.15

ahlen

-0.14

lsru

-0.14

åĪ¶

-0.14

repid

-0.14

okus

-0.14

uffling

-0.14

Ã¤ft

-0.14

anner

-0.14

POSITIVE LOGITS

tir

0.34

ram

0.32

mon

0.29

 tangent

0.28

 rant

0.27

itr

0.27

tir

0.26

 lengthy

0.24

 lecture

0.23

di

0.23

Activations Density 0.237%

elements of exaggerated storytelling or melodrama

No Comments

No Known Activations