INDEX

Explanations

statistical comparisons and analyses related to audience preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Ð´ÐµÑĢ

-0.15

afi

-0.15

lew

-0.14

afd

-0.14

VertexArray

-0.14

uing

-0.13

Ø«Ø§ÙĦ

-0.13

xs

-0.13

agate

-0.13

Tam

-0.13

POSITIVE LOGITS

 apart

0.21

 Apart

0.19

Apart

0.18

 Till

0.16

 majority

0.15

 Antony

0.15

 Majority

0.14

 till

0.14

spath

0.14

yap

0.14

Activations Density 0.348%

statistical comparisons and analyses related to audience preferences

No Comments

No Known Activations