INDEX

Explanations

instructions related to assigning values or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

loat

-0.21

onium

-0.19

indh

-0.16

 nowhere

-0.16

rys

-0.15

reamble

-0.15

enton

-0.15

ERSHEY

-0.14

ucson

-0.14

 Foley

-0.14

POSITIVE LOGITS

0.18

Å¡it

0.16

æĭŁ

0.15

eline

0.15

azing

0.15

 Kurulu

0.14

ooth

0.14

.Mapping

0.14

/string

0.14

Activations Density 0.018%

instructions related to assigning values or properties

No Comments

No Known Activations