INDEX

Explanations

numerical values and associated formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

elay

-0.17

ATO

-0.16

è¬

-0.15

 Saul

-0.14

atcher

-0.14

agnost

-0.14

['__

-0.14

-major

-0.14

elle

-0.13

áº»

-0.13

POSITIVE LOGITS

ÐĴÑĸÐ´

0.15

 lipstick

0.14

ADVERTISEMENT

0.14

illion

0.14

lick

0.14

etak

0.14

ibar

0.13

ãĤ·ãĥ§

0.13

ÑĤÐ¸Ðº

0.13

ãĤ¹ãĤ³

0.13

Activations Density 0.004%

numerical values and associated formatting

No Comments

No Known Activations