INDEX

Explanations

expressions of confusion or uncertainty related to new experiences or learning

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atori

-0.15

à¸ģà¸£à¸£à¸¡

-0.15

aked

-0.14

áº©m

-0.14

auty

-0.14

idlo

-0.14

 span

-0.14

XT

-0.13

isci

-0.13

POSITIVE LOGITS

IPA

0.17

uggage

0.16

>NN

0.16

celik

0.15

Slave

0.14

$LANG

0.14

idas

0.14

ä¹ł

0.14

rias

0.14

_NR

0.14

Activations Density 0.121%

expressions of confusion or uncertainty related to new experiences or learning

No Comments

No Known Activations