INDEX

Explanations

discussions on the psychological impacts of loss and gain in decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oria

-0.16

åįĵ

-0.15

plet

-0.14

uffman

-0.14

faq

-0.14

orgia

-0.14

isos

-0.14

Ð²ÐµÑĤ

-0.13

azar

-0.13

 fuck

-0.13

POSITIVE LOGITS

Should

0.19

 should

0.19

 Should

0.19

should

0.19

Ð°Ð¹ÑĤÐµ

0.17

 yourself

0.17

 your

0.17

GenerationStrategy

0.16

aroo

0.16

Activations Density 0.256%

discussions on the psychological impacts of loss and gain in decision-making

No Comments

No Known Activations