INDEX

Explanations

specific locations and structural elements in a text related to real estate and infrastructure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uran

-0.17

æ¹

-0.16

.BLL

-0.15

gra

-0.15

stu

-0.14

ega

-0.14

uba

-0.14

isky

-0.14

marker

-0.14

 Floor

-0.14

POSITIVE LOGITS

 ÙĪÙģÙĬ

0.19

 context

0.18

 otherwise

0.17

otherwise

0.17

 regard

0.17

 fashion

0.17

 contexts

0.16

context

0.15

Ã¤nner

0.15

 behalf

0.15

Activations Density 0.805%

specific locations and structural elements in a text related to real estate and infrastructure

No Comments

No Known Activations