INDEX

Explanations

references to specific routes and navigation paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ites

-0.18

ITES

-0.17

UEL

-0.17

ness

-0.17

uel

-0.16

lyn

-0.16

à¤²à¤¤

-0.16

éĥİ

-0.16

nek

-0.15

ding

-0.15

POSITIVE LOGITS

inely

0.21

ledge

0.18

anova

0.17

cipher

0.17

(Route

0.17

imulator

0.17

illard

0.16

etting

0.16

.route

0.16

ayer

0.15

Activations Density 0.021%

references to specific routes and navigation paths

No Comments

No Known Activations