INDEX

Explanations

variations of the word "mut."

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

ed

-0.16

aug

-0.16

haled

-0.15

idon

-0.15

off

-0.15

croll

-0.14

inkle

-0.14

oze

-0.14

endir

-0.14

rest

-0.14

POSITIVE LOGITS

mut

0.25

Mut

0.24

agen

0.24

mut

0.23

ual

0.23

 Mutual

0.23

iple

0.22

 mutual

0.22

MUT

0.21

Mut

0.21

Activations Density 0.008%

variations of the word "mut."

No Comments

No Known Activations