INDEX

Explanations

references to encyclopedic or informational content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ContextHolder

-0.17

engin

-0.15

Montserrat

-0.15

datap

-0.14

rouch

-0.14

ÑĦÐ¸

-0.14

ÎµÎ»

-0.13

iles

-0.13

PRS

-0.13

 mans

-0.13

POSITIVE LOGITS

enc

0.39

 encyclopedia

0.37

Enc

0.36

 Encyclopedia

0.36

Enc

0.34

ency

0.32

_Enc

0.30

lopedia

0.27

 entry

0.25

.Enc

0.25

Activations Density 0.098%

references to encyclopedic or informational content

No Comments

No Known Activations