INDEX

Explanations

variations of the word "will" indicating certainty or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

edu

-0.15

oidal

-0.15

chet

-0.15

ancellable

-0.15

istas

-0.15

illions

-0.14

yon

-0.14

elor

-0.14

opr

-0.14

well

-0.14

POSITIVE LOGITS

iams

0.38

iam

0.34

be

0.34

0.33

 likely

0.30

IAM

0.28

kommen

0.28

fully

0.28

power

0.26

Activations Density 0.340%

variations of the word "will" indicating certainty or expectation

No Comments

No Known Activations