INDEX

Explanations

phrases and variations of the word "belong" indicating relationships or affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

IDER

-0.17

resse

-0.16

iders

-0.15

ider

-0.15

ffe

-0.14

utr

-0.14

icle

-0.14

Î¼ÎŃ

-0.14

ulle

-0.14

lle

-0.14

POSITIVE LOGITS

 belong

0.25

 belongs

0.21

 belonged

0.21

belongs

0.19

ief

0.18

endir

0.18

(ed

0.17

å±ŀ

0.17

azer

0.16

ence

0.16

Activations Density 0.012%

phrases and variations of the word "belong" indicating relationships or affiliations

No Comments

No Known Activations