INDEX

Explanations

expressions of uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rate

-0.15

onta

-0.15

unlikely

-0.14

corp

-0.14

serter

-0.14

gs

-0.13

chod

-0.13

rava

-0.13

igma

-0.13

ocs

-0.13

POSITIVE LOGITS

 exactly

0.32

how

0.32

 about

0.30

why

0.28

 precisely

0.24

 whether

0.24

how

0.23

 Exactly

0.23

about

0.22

 what

0.22

Activations Density 0.018%

expressions of uncertainty or doubt

No Comments

No Known Activations