INDEX

Explanations

words related to communication and notification regarding appointments and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ibus

-0.14

iane

-0.13

 nackte

-0.13

pend

-0.13

enti

-0.13

 eskort

-0.13

/packages

-0.13

athers

-0.12

à¥Ģà¤£

-0.12

POSITIVE LOGITS

 whenever

0.51

 when

0.47

when

0.41

 quando

0.38

 cuando

0.37

khi

0.36

if

0.36

	when

0.35

 wenn

0.35

 náº¿u

0.32

Activations Density 0.287%

words related to communication and notification regarding appointments and actions

No Comments

No Known Activations