INDEX

Explanations

terms related to communication or commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

usp

-0.15

segue

-0.14

ansi

-0.14

AILS

-0.14

Mig

-0.14

Mil

-0.14

Pek

-0.14

ombok

-0.14

lename

-0.14

landers

-0.14

POSITIVE LOGITS

iser

0.32

uni

0.28

ision

0.27

ens

0.27

ended

0.26

encing

0.26

UNITY

0.26

unit

0.24

unique

0.23

unes

0.22

Activations Density 0.007%

terms related to communication or commentary

No Comments

No Known Activations