INDEX

Explanations

numerical data and group information from a dataset

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

 norge

-0.16

pill

-0.15

 Tribe

-0.14

ãģıãĤĮ

-0.14

inand

-0.14

esian

-0.14

 åı¸

-0.14

.elementAt

-0.14

:animated

-0.14

esus

-0.14

POSITIVE LOGITS

å¾®è½¯éĽħé»ĳ

0.14

.RunWith

0.14

 Elias

0.14

fot

0.14

kla

0.14

tal

0.13

TTY

0.13

DidLoad

0.13

ÙĦØ§ÙĦ

0.13

 Miranda

0.13

Activations Density 0.011%

numerical data and group information from a dataset

No Comments

No Known Activations

numerical data and group information from a dataset

No Comments

No Known Activations