INDEX

Explanations

terms and references related to a specific television series or its production details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

JKLM

-0.16

zyst

-0.16

ÑĥÑĢÐµ

-0.15

_WP

-0.15

 ########.

-0.15

YLE

-0.15

olley

-0.15

.apiUrl

-0.14

yle

-0.14

HCI

-0.14

POSITIVE LOGITS

 Mandal

0.38

Fav

0.27

 Baby

0.27

 bounty

0.27

Bob

0.26

MAND

0.26

Din

0.26

 Bounty

0.25

 mand

0.25

Gro

0.25

Activations Density 0.007%

terms and references related to a specific television series or its production details

No Comments

No Known Activations