INDEX

Explanations

elements related to television show production and cast information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ifton

-0.16

utherland

-0.15

.viewport

-0.15

å±ħ

-0.15

ught

-0.15

loid

-0.14

 Snyder

-0.14

ixin

-0.14

hPa

-0.14

ozem

-0.14

POSITIVE LOGITS

TV

0.20

 pilot

0.20

 episode

0.20

 episodes

0.20

episode

0.19

segments

0.19

segment

0.18

 voice

0.18

 Episode

0.18

 Pilot

0.18

Activations Density 0.005%

elements related to television show production and cast information

No Comments

No Known Activations