INDEX

Explanations

phrases related to return and refund policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

licit

-0.16

-0.14

eneg

-0.14

ritel

-0.13

enberg

-0.13

ercial

-0.13

ogn

-0.13

ruÅ¾

-0.13

DataContract

-0.13

velt

-0.13

POSITIVE LOGITS

 refund

0.48

 refunds

0.44

Ref

0.40

 refunded

0.40

refund

0.39

-ref

0.36

Ref

0.35

REF

0.34

/ref

0.33

.ref

0.32

Activations Density 0.056%

phrases related to return and refund policies

No Comments

No Known Activations