INDEX

Explanations

phrases indicating possibility or capacity

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

shima

-0.20

borough

-0.17

ãĤ¤ãĥ³ãĥĪ

-0.16

Resize

-0.16

ekl

-0.15

·æĸ°

-0.15

bid

-0.15

ÃĿ

-0.15

stk

-0.14

 Halk

-0.14

POSITIVE LOGITS

ingleton

0.21

 written

0.19

 reform

0.19

 Written

0.19

 expressed

0.18

 regard

0.18

Express

0.18

 write

0.18

Written

0.18

 construct

0.17

Activations Density 0.084%

phrases indicating possibility or capacity

No Comments

No Known Activations