INDEX

Explanations

themes related to self-worth and validation

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

Ú©Ø´

-0.17

annies

-0.15

 oportun

-0.14

efd

-0.14

ensa

-0.14

ãĥ³ãĤ¹

-0.14

imu

-0.14

Ã¨s

-0.13

ammen

-0.13

POSITIVE LOGITS

 Summers

0.15

ÑĤÐ°Ð»

0.14

´

0.14

alli

0.14

yro

0.14

casecmp

0.14

SCM

0.14

age

0.13

ãĥ¼ãĤ

0.13

Activations Density 0.507%

themes related to self-worth and validation

No Comments

No Known Activations