INDEX

Explanations

references to people or entities being addressed or involved

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

isci

-0.18

okie

-0.16

ARS

-0.14

zos

-0.14

 Ð³ÑĢÐ¾Ð¼

-0.14

ÑĢÐ¾Ð³

-0.13

.setParameter

-0.13

 Shan

-0.13

eken

-0.13

POSITIVE LOGITS

 with

0.34

with

0.28

 avec

0.25

 dengan

0.23

	with

0.22

 vá»Ľi

0.22

ewith

0.21

swith

0.20

 withObject

0.20

WithString

0.19

Activations Density 0.048%

references to people or entities being addressed or involved

No Comments

No Known Activations