INDEX

Explanations

variations of the term "Mit" related to organizations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

yms

-0.17

ALAR

-0.15

ãĤ¯ãĥĪ

-0.14

etyl

-0.14

WEEN

-0.14

hem

-0.14

edList

-0.14

ist

-0.14

onta

-0.14

hound

-0.14

POSITIVE LOGITS

ochond

0.29

igation

0.26

ubishi

0.23

igate

0.22

igated

0.21

zv

0.19

osis

0.19

IGATION

0.18

Mit

0.17

igator

0.17

Activations Density 0.016%

variations of the term "Mit" related to organizations or institutions

No Comments

No Known Activations