INDEX

Explanations

words related to uncertainty and conditionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

å¨ĺ

-0.15

ownik

-0.15

ezi

-0.14

zzle

-0.14

ziej

-0.14

imary

-0.14

xac

-0.14

ë§ģ

-0.14

SizePolicy

-0.14

.tc

-0.14

POSITIVE LOGITS

 Poll

0.16

ahan

0.15

 Cassidy

0.14

Poll

0.14

cao

0.14

 environment

0.14

 delic

0.14

Tu

0.14

 Shannon

0.14

Activations Density 0.000%

words related to uncertainty and conditionals

No Comments

No Known Activations