INDEX

Explanations

legal terminology and references to court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

á»Ľp

-0.18

akest

-0.15

arest

-0.15

Ð°Ð»Ñİ

-0.15

//===

-0.14

 Worker

-0.14

asbourg

-0.14

VML

-0.14

Ä°Åŀ

-0.14

 Tribunal

-0.14

POSITIVE LOGITS

dem

0.19

mes

0.19

 replication

0.19

 bill

0.18

 assignments

0.18

Įĵ

0.17

 prayed

0.16

atrix

0.16

 aver

0.16

aver

0.16

Activations Density 0.122%

legal terminology and references to court cases

No Comments

No Known Activations