INDEX

Explanations

references to authority and justification in decision-making contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

zym

-0.17

ÏħÎ¼

-0.16

ensex

-0.15

Î½Î¹Î±

-0.15

SYM

-0.15

acz

-0.15

IMS

-0.14

stÃ¥

-0.14

ederland

-0.14

POSITIVE LOGITS

ãģªãģĳãĤĮãģ°

0.15

ï¼ĮåĪĻ

0.15

esse

0.15

 anywhere

0.15

Ã¦re

0.14

 yoksa

0.14

Ä°L

0.14

 varsa

0.14

ount

0.14

ess

0.14

Activations Density 0.129%

references to authority and justification in decision-making contexts

No Comments

No Known Activations