INDEX

Explanations

references to judicial discretion and its application in court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

çĪŃ

-0.16

 argue

-0.15

 claim

-0.15

 arguing

-0.15

claim

-0.15

 complaining

-0.14

 getLogger

-0.14

 lobbying

-0.14

 ense

-0.14

 stehen

-0.14

POSITIVE LOGITS

 hearing

0.25

 hear

0.23

pron

0.23

heard

0.22

 Hearing

0.21

 pron

0.21

 heard

0.21

 entertain

0.20

adj

0.19

consider

0.19

Activations Density 0.101%

references to judicial discretion and its application in court rulings

No Comments

No Known Activations