INDEX

Explanations

references to television series and their 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

cene

-0.16

.sf

-0.15

Ã³s

-0.15

æĪ

-0.14

 Ekon

-0.14

ilde

-0.14

Ð°ÑĤÐµÐ³Ð¾ÑĢ

-0.14

arrass

-0.14

(ld

-0.14

"},"

-0.14

POSITIVE LOGITS

 animation

0.32

 animated

0.32

 Cartoon

0.32

 anim

0.32

Cart

0.31

 Animation

0.29

 cartoons

0.29

 Anim

0.28

 cartoon

0.27

.Cart

0.27

Activations Density 0.080%

references to television series and their production details

No Comments

No Known Activations