INDEX

Explanations

key terms associated with legal and medical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ESP

-0.16

akan

-0.16

ANCH

-0.14

 Dresses

-0.14

upo

-0.14

ÑĥÑĢÐµ

-0.14

ption

-0.14

holds

-0.13

POSITIVE LOGITS

EdgeInsets

0.15

 Entered

0.15

ikk

0.14

Entered

0.14

odom

0.14

owi

0.14

Vim

0.13

zee

0.13

 Loren

0.13

udge

0.13

Activations Density 0.008%

key terms associated with legal and medical concepts

No Comments

No Known Activations