INDEX

Explanations

comparisons between different literary works or themes

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

inch

-0.16

illon

-0.16

normally

-0.15

 compromise

-0.14

illin

-0.13

anki

-0.13

å¹²

-0.13

acent

-0.13

Normally

-0.13

resh

-0.13

POSITIVE LOGITS

 similarities

0.43

 similarity

0.36

 similar

0.34

 Similar

0.30

 simil

0.29

çĽ¸åĲĮ

0.29

similar

0.29

imilar

0.29

Similar

0.29

 identical

0.29

Activations Density 0.282%

comparisons between different literary works or themes

No Comments

No Known Activations