INDEX

Explanations

dialogue and conversational interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

LOY

-0.14

.quest

-0.14

Muk

-0.14

zas

-0.14

burgh

-0.13

utex

-0.13

ddb

-0.13

iminal

-0.13

ritz

-0.13

 Cosmos

-0.13

POSITIVE LOGITS

sir

0.64

Sir

0.52

Sir

0.50

åħĪçĶŁ

0.35

Mr

0.34

Mr

0.31

 boss

0.27

 Boss

0.24

Boss

0.23

 Professor

0.21

Activations Density 0.572%

dialogue and conversational interactions between characters

No Comments

No Known Activations