INDEX

Explanations

references to rankings, popularity, and top-rated items in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÏĨÎ¹

-0.17

enthal

-0.16

ument

-0.15

angelo

-0.13

enze

-0.13

ãĥĭãĥĥãĤ¯

-0.13

bler

-0.13

criptor

-0.13

 generations

-0.13

ãĥ³ãĥĹ

-0.13

POSITIVE LOGITS

 overall

0.26

gross

0.25

 gross

0.25

-ranked

0.24

 performing

0.24

-selling

0.23

 earners

0.23

 rated

0.23

-rated

0.23

-ranking

0.22

Activations Density 0.071%

references to rankings, popularity, and top-rated items in various contexts

No Comments

No Known Activations