INDEX

Explanations

references to gameplay mechanics and complexity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rega

-0.16

phen

-0.16

azes

-0.15

iyah

-0.15

breadcrumb

-0.14

quer

-0.14

ÅĤem

-0.14

ÑģÑĮÐº

-0.14

ousand

-0.14

POSITIVE LOGITS

 pref

0.15

.LookAndFeel

0.15

anne

0.14

Mud

0.14

 Eleanor

0.14

adaÅŁ

0.14

iT

0.13

 Chow

0.13

oint

0.13

 wouldn

0.13

Activations Density 0.198%

references to gameplay mechanics and complexity

No Comments

No Known Activations