INDEX

Explanations

terms related to organizational structure and infrastructure changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 subur

-0.17

readcr

-0.16

vik

-0.15

heimer

-0.15

vous

-0.15

ohen

-0.15

ãĥ¼ãĥĪ

-0.15

rellas

-0.14

uttle

-0.14

amax

-0.14

POSITIVE LOGITS

 altogether

0.73

 entirely

0.53

alto

0.43

 completely

0.42

 Alto

0.36

 Completely

0.35

 totally

0.30

 entire

0.30

 Entire

0.30

 completamente

0.27

Activations Density 0.247%

terms related to organizational structure and infrastructure changes

No Comments

No Known Activations