INDEX

Explanations

references to "past" and related concepts regarding history or previous events

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

endon

-0.19

åĻ¨

-0.18

fter

-0.17

lei

-0.16

annes

-0.16

ismo

-0.15

ered

-0.15

thing

-0.15

zb

-0.14

viÄį

-0.14

POSITIVE LOGITS

ebin

0.38

imes

0.34

ime

0.32

iche

0.31

 tense

0.30

/current

0.30

ries

0.27

eur

0.26

ures

0.26

-present

0.26

Activations Density 0.033%

references to "past" and related concepts regarding history or previous events

No Comments

No Known Activations