INDEX

Explanations

contextual conditions and factors related to variations in experiences or expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ermann

-0.16

 ways

-0.16

zes

-0.16

echan

-0.14

Principal

-0.14

aleb

-0.14

inka

-0.14

utschen

-0.14

abra

-0.13

ark

-0.13

POSITIVE LOGITS

 whether

0.26

 circumstance

0.25

 circumstances

0.25

whether

0.23

age

0.20

 individual

0.20

Whether

0.19

 type

0.19

 Whether

0.19

zda

0.19

Activations Density 0.084%

contextual conditions and factors related to variations in experiences or expectations

No Comments

No Known Activations