INDEX

Explanations

references to legal and financial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onta

-0.15

oine

-0.15

 GÃ¼r

-0.14

EZ

-0.14

 gá»ĳc

-0.14

 ìłĦë¬¸

-0.14

lein

-0.14

fed

-0.14

.dm

-0.14

POSITIVE LOGITS

 advice

0.19

 advised

0.18

Advice

0.17

Spin

0.17

 counsel

0.17

 advise

0.16

 Advice

0.16

uder

0.16

 Spin

0.16

spin

0.15

Activations Density 0.033%

references to legal and financial terms

No Comments

No Known Activations