INDEX

Explanations

markup or formatting indicators used in text documents

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

chw

-0.16

uality

-0.16

oken

-0.16

 grav

-0.15

 bull

-0.14

ØªÙĪØ±

-0.14

com

-0.14

 ICON

-0.14

à¸Ļà¸ª

-0.13

ernel

-0.13

POSITIVE LOGITS

#↵↵

0.20

###↵↵

0.17

 abstract

0.16

##↵↵

0.15

ouro

0.15

uD

0.15

Rag

0.15

.scalablytyped

0.15

0.14

 fitte

0.14

Activations Density 0.008%

markup or formatting indicators used in text documents

No Comments

No Known Activations