INDEX

Explanations

gerunds, particularly focusing on actions related to processes or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ings

-0.38

/remove

-0.35

/disable

-0.28

/write

-0.24

/delete

-0.24

INGS

-0.23

ÂŃing

-0.23

/update

-0.23

ingly

-0.22

/do

-0.22

POSITIVE LOGITS

/loading

0.33

ly

0.32

/testing

0.31

redients

0.28

/logging

0.27

redient

0.26

ness

0.25

/rem

0.25

ton

0.24

/up

0.23

Activations Density 0.876%

gerunds, particularly focusing on actions related to processes or tasks

No Comments

No Known Activations

gerunds, particularly focusing on actions related to processes or tasks

No Comments

No Known Activations