INDEX

Explanations

instances of significant or unusual events related to danger or caution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

udu

-0.14

@nate

-0.14

anas

-0.14

.gdx

-0.14

mun

-0.14

ULT

-0.13

omics

-0.13

antis

-0.13

ensation

-0.13

POSITIVE LOGITS

 then

0.22

then

0.18

 followed

0.18

Then

0.17

çĦ¶åĲİ

0.17

 Then

0.16

ï¼ĮçĦ¶åĲİ

0.16

 à¹ģà¸¥

0.15

 pert

0.15

 THEN

0.15

Activations Density 0.144%

instances of significant or unusual events related to danger or caution

No Comments

No Known Activations