INDEX

Explanations

expressions of skepticism and potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

UDA

-0.18

 approximately

-0.17

]={↵

-0.17

.scalablytyped

-0.16

atform

-0.15

 Approximately

-0.15

izza

-0.15

ish

-0.15

Ã¤ge

-0.15

 roughly

-0.15

POSITIVE LOGITS

 perfectly

0.17

 tomorrow

0.17

may

0.17

Å¡ak

0.16

 Completely

0.15

 completely

0.15

 maybe

0.14

Zuk

0.14

#__

0.14

à¤¬à¤°

0.14

Activations Density 0.201%

expressions of skepticism and potential outcomes

No Comments

No Known Activations