INDEX

Explanations

references to advertisements and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ľi

-0.17

Ð¾ÐºÐµ

-0.15

 ÑĢÐ°ÑģÑĩ

-0.15

 edip

-0.14

ÑĥÐ´Ð¸

-0.14

otten

-0.14

Î³ÎµÎ¹

-0.14

 ÑģÑĤÐ¾

-0.14

èģ²

-0.14

.thumb

-0.14

POSITIVE LOGITS

 full

0.16

 exclusive

0.15

Bot

0.15

 outr

0.15

 integration

0.15

Bot

0.15

bot

0.14

 executive

0.14

Pap

0.14

Activations Density 0.012%

references to advertisements and related terminology

No Comments

No Known Activations