INDEX

Explanations

references to educational institutions and academic achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

occo

-0.16

orem

-0.16

 Farrell

-0.14

FW

-0.14

èĥľ

-0.14

sen

-0.14

setQuery

-0.14

ãĤ»ãĥ³

-0.14

illo

-0.14

iche

-0.13

POSITIVE LOGITS

 Harvard

0.36

 Princeton

0.34

 Yale

0.33

 Stanford

0.32

MIT

0.31

 Columbia

0.30

inceton

0.28

 Dart

0.28

MIT

0.28

 Cornell

0.25

Activations Density 0.090%

references to educational institutions and academic achievements

No Comments

No Known Activations