INDEX

Explanations

statements indicating the existence or occurrence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

isty

-0.16

æĥł

-0.15

ozor

-0.15

\application

-0.14

gon

-0.14

oples

-0.14

iginal

-0.14

elist

-0.14

iales

-0.14

VERR

-0.14

POSITIVE LOGITS

arg

0.16

 clear

0.16

ima

0.15

antic

0.15

ourt

0.15

 Fare

0.15

 aver

0.15

Ton

0.15

à¸ĵ

0.14

 fore

0.14

Activations Density 0.085%

statements indicating the existence or occurrence of something

No Comments

No Known Activations