INDEX

Explanations

terms related to intentional actions and deception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

quette

-0.15

;element

-0.15

avings

-0.15

ier

-0.14

ombies

-0.14

ensitive

-0.14

rani

-0.13

Ð°Ð½ÑĤÐ°

-0.13

rel

-0.13

/Area

-0.13

POSITIVE LOGITS

chos

0.17

ystone

0.17

ystore

0.16

 intentional

0.16

ewriter

0.15

Rub

0.15

©

0.15

ÑģÐ¸Ñı

0.15

Ju

0.15

Activations Density 0.030%

terms related to intentional actions and deception

No Comments

No Known Activations