INDEX

Explanations

references to historical buildings and their transformations

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

strup

-0.22

ãĥªãĤ«

-0.15

statt

-0.14

//{{

-0.14

reature

-0.14

resco

-0.14

ixon

-0.13

.Atomic

-0.13

.reload

-0.13

esture

-0.13

POSITIVE LOGITS

ADA

0.16

ardo

0.16

0.14

 èĲ¬

0.14

zym

0.14

adaptive

0.13

 shoes

0.13

ÐµÑĦ

0.13

omen

0.13

anda

0.13

Activations Density 0.139%

references to historical buildings and their transformations

No Comments

No Known Activations