INDEX

Explanations

entities and names related to legal professions and healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.16

Url

-0.15

-0.14

 hÃ³a

-0.14

å¢¨

-0.14

 Camping

-0.14

igar

-0.13

æ®

-0.13

ua

-0.13

POSITIVE LOGITS

abd

0.17

ogg

0.16

ierz

0.15

,strlen

0.15

celik

0.15

equality

0.14

defs

0.14

stras

0.14

elage

0.14

 eskort

0.13

Activations Density 0.072%

entities and names related to legal professions and healthcare

No Comments

No Known Activations