INDEX

Explanations

expressions related to possession and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

áº©m

-0.15

rb

-0.15

ãĤ¾

-0.14

ÏģÎµÏĤ

-0.14

iesen

-0.14

Reviewer

-0.13

 Liga

-0.13

.dev

-0.13

ArrayOf

-0.13

gere

-0.13

POSITIVE LOGITS

ecess

0.17

ceb

0.15

fat

0.14

rove

0.14

rose

0.14

CE

0.14

 Fritz

0.14

ycastle

0.14

mtree

0.14

ccione

0.14

Activations Density 0.031%

expressions related to possession and ownership

No Comments

No Known Activations