INDEX

Explanations

expressions of gratitude or acknowledgment of generosity

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

 lever

-0.16

XHR

-0.15

ÐµÐ¹

-0.15

Ã²n

-0.15

croft

-0.14

olesterol

-0.14

/UIKit

-0.14

enge

-0.14

avy

-0.14

olik

-0.14

POSITIVE LOGITS

uÅŁ

0.16

 Pipes

0.14

udad

0.14

ç¿¼

0.14

pike

0.14

merc

0.14

acha

0.13

inely

0.13

 practical

0.13

occus

0.13

Activations Density 0.004%

expressions of gratitude or acknowledgment of generosity

No Comments

No Known Activations