INDEX

Explanations

terms related to legal precedents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÙĪØ±Øª

-0.15

UG

-0.15

irs

-0.15

oll

-0.15

 ÑģÑİ

-0.15

oline

-0.14

owns

-0.14

ink

-0.14

ago

-0.14

nes

-0.14

POSITIVE LOGITS

upy

0.17

umer

0.17

ived

0.15

PEND

0.15

zeitig

0.15

ively

0.14

arkan

0.14

roupe

0.14

otime

0.14

Äĩi

0.14

Activations Density 0.003%

terms related to legal precedents

No Comments

No Known Activations