INDEX

Explanations

characters' actions and dialogue in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð½Ð°ÑĤ

-0.16

ilton

-0.15

onen

-0.14

uste

-0.14

swire

-0.13

regor

-0.13

 Deniz

-0.13

omor

-0.13

zial

-0.13

æĻ®

-0.13

POSITIVE LOGITS

ctal

0.15

elocity

0.14

à¤¾à¤¨à¤¸

0.14

ucks

0.14

owing

0.13

 Couch

0.13

ims

0.13

Eth

0.13

Activations Density 1.515%

characters' actions and dialogue in the text

No Comments

No Known Activations