INDEX

Explanations

proper nouns or specific references within a context

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

 vente

-0.16

ÑĪÐ¸ÑģÑĮ

-0.15

 ÑģÐ¾Ð±Ð¾Ð¹

-0.14

zell

-0.14

romium

-0.14

losures

-0.14

ÑĥÑĩ

-0.14

åĬŀåħ¬

-0.14

cela

-0.14

Ùħ

-0.14

POSITIVE LOGITS

co

0.15

 Arts

0.15

 Tier

0.14

cmp

0.14

ARP

0.14

 arts

0.14

 operator

0.14

arin

0.13

aru

0.13

yak

0.13

Activations Density 0.000%

proper nouns or specific references within a context

No Comments

No Known Activations