INDEX

Explanations

references to historical figures and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

skou

-0.17

mium

-0.16

serter

-0.15

 roma

-0.14

iveau

-0.14

 "(\<

-0.14

.bridge

-0.14

rompt

-0.14

pta

-0.13

eki

-0.13

POSITIVE LOGITS

 Count

0.43

 Earl

0.40

 count

0.40

 Lord

0.38

ear

0.37

 Counts

0.36

Ear

0.35

 counts

0.35

 Duke

0.34

Count

0.33

Activations Density 0.075%

references to historical figures and their titles

No Comments

No Known Activations