INDEX

Explanations

future tense verbs and expressions indicating intentions or plans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 yourselves

-0.18

 themselves

-0.17

 ActiveSupport

-0.17

aÄŁÄ±

-0.14

emand

-0.14

 itself

-0.14

á»Ĳ

-0.13

enville

-0.13

ilm

-0.13

asy

-0.13

POSITIVE LOGITS

be

0.22

 miss

0.21

bet

0.19

 definitely

0.18

DEF

0.17

 defin

0.17

 keep

0.17

 spare

0.16

 bets

0.16

 Definitely

0.16

Activations Density 0.088%

future tense verbs and expressions indicating intentions or plans

No Comments

No Known Activations

future tense verbs and expressions indicating intentions or plans

No Comments

No Known Activations