INDEX

Explanations

phrases that indicate adventure or exploration

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

soever

-0.18

zelf

-0.17

ched

-0.16

ï½į

-0.16

eyer

-0.16

bie

-0.15

Ð¾ÑĢÐ¾

-0.15

ampa

-0.15

ynchron

-0.15

AKE

-0.14

POSITIVE LOGITS

tainment

0.16

LAB

0.15

ined

0.15

ires

0.15

ous

0.15

ry

0.15

itious

0.14

egl

0.14

ial

0.14

Activations Density 0.033%

phrases that indicate adventure or exploration

No Comments

No Known Activations