INDEX

Explanations

legal terminology and references to court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ernals

-0.16

ToWorld

-0.15

roj

-0.15

Äł

-0.15

ekk

-0.14

roker

-0.14

ê³¡

-0.14

.mousePosition

-0.14

-modal

-0.14

modal

-0.14

POSITIVE LOGITS

 pleas

0.18

 charged

0.18

 plea

0.18

 pled

0.17

 guilty

0.17

_DEF

0.16

gu

0.15

charged

0.15

 charges

0.15

 charge

0.15

Activations Density 0.058%

legal terminology and references to court proceedings

No Comments

No Known Activations