INDEX

Explanations

action verbs that imply processes, appointments, or interruptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

quina

-0.15

ATE

-0.15

lap

-0.14

Ùĩ

-0.14

pmat

-0.14

iche

-0.14

usal

-0.14

/testing

-0.14

icable

-0.14

ARP

-0.13

POSITIVE LOGITS

[s

0.50

(s

0.41

sWith

0.39

Ñķ

0.36

es

0.36

sthrough

0.33

sto

0.33

ä»¬

0.31

à¥įà¤¸

0.31

swith

0.29

Activations Density 0.126%

action verbs that imply processes, appointments, or interruptions

No Comments

No Known Activations