INDEX

Explanations

references to hidden fees and costs associated with financial transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

mmo

-0.16

elman

-0.15

éĢł

-0.14

ohn

-0.14

 vouchers

-0.14

ãĥ¼ãĥĪ

-0.13

à¸Ńà¸ŀ

-0.13

 narrowing

-0.13

pek

-0.13

é

-0.13

POSITIVE LOGITS

 terms

0.20

/terms

0.17

 Terms

0.16

 hidden

0.16

hidden

0.16

terms

0.15

 penalties

0.15

 penal

0.15

rip

0.15

 Hidden

0.14

Activations Density 0.035%

references to hidden fees and costs associated with financial transactions

No Comments

No Known Activations