INDEX

Explanations

terms related to legal processes and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

æĶ¿çŃĸ

-0.15

.eth

-0.15

.pkg

-0.15

attles

-0.15

ched

-0.14

ITTE

-0.14

utz

-0.14

uet

-0.13

 Task

-0.13

bum

-0.13

POSITIVE LOGITS

 cass

0.25

rog

0.20

 Cass

0.20

 Chamber

0.18

 subsidi

0.18

 procedure

0.18

 proceedings

0.18

 procedural

0.17

 chamber

0.17

 dilig

0.17

Activations Density 0.043%

terms related to legal processes and representation

No Comments

No Known Activations