INDEX

Explanations

references to rights or entitlements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

uben

-0.14

áº¿n

-0.14

 Ware

-0.14

ÑĢÑĸÐ´

-0.14

uple

-0.14

onym

-0.14

pars

-0.14

rol

-0.14

Ø§Ø±Ùĩ

-0.14

Op

-0.13

POSITIVE LOGITS

 reserved

0.46

 Reserved

0.41

reserved

0.36

 reserve

0.35

Reserved

0.33

 RESERVED

0.31

 reserves

0.29

_reserved

0.29

 Reserve

0.28

 reserv

0.25

Activations Density 0.004%

references to rights or entitlements

No Comments

No Known Activations