INDEX

Explanations

phrases or references that highlight specific decisions or options regarding various topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

jaw

-0.16

ible

-0.15

Ven

-0.15

Voj

-0.14

seo

-0.14

 Cafe

-0.14

pak

-0.14

Caj

-0.14

OPS

-0.14

zens

-0.14

POSITIVE LOGITS

mscorlib

0.15

/topics

0.15

istique

0.15

adla

0.14

Fi

0.14

Fi

0.14

¥Ĳ

0.14

meli

0.14

 onCancel

0.14

elly

0.14

Activations Density 0.331%

phrases or references that highlight specific decisions or options regarding various topics

No Comments

No Known Activations