INDEX

Explanations

emotional reactions and opinions about media experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ISA

-0.16

leen

-0.14

 Exactly

-0.14

å±Ĭ

-0.14

Woo

-0.14

rolley

-0.13

ETO

-0.13

à¤¬à¤²

-0.13

woo

-0.13

tom

-0.13

POSITIVE LOGITS

 overall

0.21

 Overall

0.20

Overall

0.20

overall

0.18

 felt

0.15

acam

0.15

odon

0.15

chio

0.15

rike

0.15

ogle

0.14

Activations Density 0.346%

emotional reactions and opinions about media experiences

No Comments

No Known Activations