INDEX

Explanations

numerical values or figures followed by specific terms or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 weather

-0.17

wet

-0.16

PropTypes

-0.16

ogn

-0.16

Wet

-0.15

]]>

-0.14

 Weather

-0.14

ronic

-0.14

ÑĢÐ´

-0.14

brands

-0.13

POSITIVE LOGITS

IMER

0.15

pleted

0.15

0.14

-prev

0.14

coe

0.14

_DECL

0.14

NC

0.14

ugi

0.14

ë¿Ĳ

0.14

raci

0.13

Activations Density 0.001%

numerical values or figures followed by specific terms or metrics

No Comments

No Known Activations