INDEX

Explanations

references to fireworks displays and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð¿Ð°ÑĤ

-0.16

 Spinner

-0.16

hiro

-0.15

Lun

-0.15

?>&

-0.15

iseum

-0.15

emes

-0.15

 Bravo

-0.14

usto

-0.14

 Äĳo

-0.14

POSITIVE LOGITS

/exp

0.16

aq

0.14

 Webb

0.14

 Piece

0.13

Î²Î¿Î»

0.13

 McMahon

0.13

shell

0.13

¢

0.13

Activations Density 0.004%

references to fireworks displays and related events

No Comments

No Known Activations