INDEX

Explanations

expressions of gratitude and requests for help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

etr

-0.16

ison

-0.16

enci

-0.15

bed

-0.15

larÄ±yla

-0.14

aan

-0.14

uche

-0.14

bd

-0.14

angelo

-0.14

tutorial

-0.14

POSITIVE LOGITS

luet

0.15

APTER

0.14

alÄ±k

0.14

 ÑĨÑı

0.14

aping

0.14

ACA

0.14

åĬĽçļĦ

0.14

/xhtml

0.14

apol

0.14

Activations Density 0.020%

expressions of gratitude and requests for help

No Comments

No Known Activations