INDEX

Explanations

terms related to credit status and financial obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

.opensource

-0.16

imat

-0.16

 insp

-0.14

aÄį

-0.14

iever

-0.14

ond

-0.14

subst

-0.14

uÃ§

-0.14

earer

-0.13

gart

-0.13

POSITIVE LOGITS

 credit

0.31

 bure

0.29

 bureau

0.28

 Credit

0.26

Equ

0.25

credit

0.24

 score

0.24

 furn

0.23

Credit

0.22

 Score

0.22

Activations Density 0.027%

terms related to credit status and financial obligations

No Comments

No Known Activations