INDEX

Explanations

locations and their details, particularly addresses

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

lasses

-0.18

RICT

-0.15

 shock

-0.14

aseline

-0.14

azer

-0.13

KB

-0.13

instein

-0.13

asis

-0.13

Ø

-0.13

æĳ

-0.13

POSITIVE LOGITS

olini

0.15

eview

0.15

Ð¾Ð»Ð°

0.15

.Spring

0.14

ãģĤ

0.14

teness

0.14

HttpException

0.13

Ĵáŀ

0.13

 coppia

0.13

sta

0.13

Activations Density 0.011%

locations and their details, particularly addresses

No Comments

No Known Activations