INDEX

Explanations

numeric data or structured information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.16

-0.15

kate

-0.15

ÙģØ§ÙĤ

-0.15

 area

-0.15

artz

-0.15

 amplified

-0.14

POSITIVE LOGITS

AINS

0.17

EMPL

0.16

ubat

0.16

éĨĴ

0.15

aign

0.15

UIAlertView

0.15

aal

0.15

IMARY

0.15

EGIN

0.15

SetActive

0.15

Activations Density 0.037%

numeric data or structured information

No Comments

No Known Activations