INDEX

Explanations

phrases that indicate uncertainty or speculation

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

 sÄħ

-0.15

ä¸Ģæł·

-0.14

@js

-0.14

ä¸Ģèµ·

-0.14

á¿¶

-0.14

same

-0.13

Same

-0.13

è»

-0.13

sla

-0.13

POSITIVE LOGITS

 nobody

0.35

few

0.29

 none

0.29

 everyone

0.26

 many

0.23

 everybody

0.22

no

0.22

 anyone

0.21

def

0.21

 NONE

0.21

Activations Density 0.215%

phrases that indicate uncertainty or speculation

No Comments

No Known Activations