INDEX

Explanations

expressions related to negotiation and 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 quant

-0.15

-0.14

dney

-0.14

 relatively

-0.14

pies

-0.14

 uphill

-0.14

(#

-0.13

.Qual

-0.13

↵

-0.13

WON

-0.13

POSITIVE LOGITS

 closer

0.20

clo

0.19

 sogar

0.18

 tháºŃm

0.18

çĶļèĩ³

0.17

 figure

0.16

 higher

0.16

 nearer

0.16

æĽ´

0.15

 bumped

0.15

Activations Density 0.263%

expressions related to negotiation and decision-making

No Comments

No Known Activations