INDEX

Explanations

references to specific architectural locations or notable structures

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

ecast

-0.17

alach

-0.14

alous

-0.14

 conver

-0.13

 tiers

-0.13

ani

-0.13

/tutorial

-0.13

ÑĢÑĥÐ½

-0.13

xico

-0.13

xEF

-0.13

POSITIVE LOGITS

esen

0.15

bilt

0.14

ional

0.14

Ø´Ø±

0.14

heets

0.14

esi

0.14

elder

0.14

allah

0.14

uddy

0.13

oses

0.13

Activations Density 0.377%

references to specific architectural locations or notable structures

No Comments

No Known Activations