INDEX

Explanations

references to historical empires and geographical regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

è¿Ľ

-0.16

éĢ²

-0.16

enez

-0.16

-0.15

 progressed

-0.15

GREE

-0.15

 Jacobs

-0.14

Pun

-0.14

ÙĪØ¹

-0.14

arend

-0.14

POSITIVE LOGITS

 NUIT

0.16

antt

0.15

cis

0.14

erken

0.14

.front

0.13

 Wind

0.13

ÙĦØ·

0.13

.wind

0.13

 fringe

0.13

Activations Density 0.094%

references to historical empires and geographical regions

No Comments

No Known Activations