INDEX

Explanations

references to gaming and interactive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

éŁ³æ¥½

-0.14

orthand

-0.14

è¾º

-0.13

snd

-0.13

avings

-0.13

ç¿Ķ

-0.13

onders

-0.13

STANCE

-0.13

Disk

-0.12

gif

-0.12

POSITIVE LOGITS

 escape

0.55

 Escape

0.51

Escape

0.43

escape

0.41

 escapes

0.41

 escaping

0.39

.escape

0.37

Esc

0.37

.Escape

0.36

 escaped

0.35

Activations Density 0.006%

references to gaming and interactive experiences

No Comments

No Known Activations