INDEX

Explanations

references to "insight" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ingular

-0.18

acher

-0.17

avra

-0.17

ober

-0.17

 Schultz

-0.15

ioc

-0.15

DBG

-0.14

PPP

-0.14

_SHARE

-0.14

fo

-0.14

POSITIVE LOGITS

Äįan

0.14

rides

0.14

xes

0.14

zie

0.13

lices

0.13

éļĬ

0.13

rippling

0.13

Fav

0.13

 onMouse

0.13

otal

0.13

Activations Density 0.006%

references to "insight" and related terms

No Comments

No Known Activations