INDEX

Explanations

the word "most" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 mappedBy

-0.16

Î´ÏĮÎ½

-0.16

inand

-0.15

agus

-0.15

atori

-0.15

 quite

-0.15

 somewhat

-0.15

 most

-0.14

aign

-0.14

rick

-0.14

POSITIVE LOGITS

 definitely

0.24

 certainly

0.23

 likely

0.22

arda

0.21

acci

0.21

 Definitely

0.21

likely

0.21

ly

0.20

 assured

0.20

afa

0.20

Activations Density 0.033%

the word "most" in various contexts

No Comments

No Known Activations