INDEX

Explanations

legal references to court cases and judgments related to liability and compensation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

hart

-0.16

æª

-0.15

à¸Ĳ

-0.15

INCT

-0.14

antine

-0.14

bler

-0.14

antino

-0.14

leigh

-0.14

strom

-0.14

starter

-0.13

POSITIVE LOGITS

 client

0.25

 Client

0.22

 clients

0.21

 defense

0.20

 summary

0.19

Client

0.19

 Confidential

0.19

 Summary

0.19

 defended

0.19

 Clients

0.19

Activations Density 0.096%

legal references to court cases and judgments related to liability and compensation

No Comments

No Known Activations