INDEX

Explanations

nouns related to digital data or technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

unction

-0.15

--

-0.14

Ã¤m

-0.13

-0.12

**

-0.12

ê¸°ê°Ģ

-0.12

 --↵

-0.12

ãĢĤèĢĮ

-0.12

amp

-0.12

innen

-0.12

POSITIVE LOGITS

:↵

0.25

 :↵

0.25

":↵

0.25

ï¼ļ↵

0.25

 :↵↵

0.24

:↵↵

0.23

:č↵

0.22

):↵

0.22

:↵↵↵

0.22

":↵↵

0.22

Activations Density 0.023%

nouns related to digital data or technology

No Comments

No Known Activations