INDEX

Explanations

sections and formatting related to legal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

æĵ¦

-0.17

hazi

-0.15

azi

-0.14

hem

-0.14

 Spray

-0.14

 Levy

-0.13

rtl

-0.13

 Intro

-0.13

å®Ī

-0.13

(){}↵

-0.13

POSITIVE LOGITS

atik

0.15

anik

0.15

atre

0.14

:NS

0.14

ulace

0.14

ï½¯

0.14

 Gand

0.14

kup

0.14

 molec

0.13

liqu

0.13

Activations Density 0.024%

sections and formatting related to legal documentation

No Comments

No Known Activations