INDEX

Explanations

names and titles relevant to legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

lis

-0.15

rtl

-0.14

entina

-0.14

uisse

-0.14

LET

-0.14

uba

-0.14

arro

-0.14

ESSAGES

-0.14

icol

-0.14

lif

-0.14

POSITIVE LOGITS

LocalizedString

0.15

uhan

0.14

ë³Ģ

0.13

.ManyToMany

0.13

ALCHEMY

0.13

Ã£ng

0.13

avenport

0.13

.openg

0.13

.capture

0.13

 intptr

0.13

Activations Density 0.018%

names and titles relevant to legal cases

No Comments

No Known Activations