INDEX

Explanations

legal references and regulations within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

nÄĽnÃŃ

-0.16

Pane

-0.15

uggestion

-0.15

uye

-0.15

 Active

-0.14

istique

-0.14

Lad

-0.14

 bols

-0.14

 rationale

-0.14

tie

-0.13

POSITIVE LOGITS

 DropIndex

0.16

etz

0.15

 GenerationType

0.15

nat

0.14

 disadv

0.14

 Aston

0.14

ÐºÐ°Ð²

0.13

_ship

0.13

Ship

0.13

.providers

0.13

Activations Density 0.010%

legal references and regulations within a document

No Comments

No Known Activations

legal references and regulations within a document

No Comments

No Known Activations