INDEX

Explanations

locations and events associated with performances or entertainment activities

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

ÏĥÎ®

-0.16

 "-//

-0.15

 Noon

-0.15

tej

-0.15

ivery

-0.15

igner

-0.14

ÙİØ¯

-0.13

thur

-0.13

aptor

-0.13

POSITIVE LOGITS

 Assembly

0.20

 Alexandra

0.18

 Empire

0.18

SEC

0.17

Fib

0.17

 Drill

0.17

 Tobacco

0.17

 Scala

0.17

ICC

0.17

Vue

0.17

Activations Density 0.034%

locations and events associated with performances or entertainment activities

No Comments

No Known Activations