INDEX

Explanations

instances of significant emotional expressions or personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Succ

-0.17

ses

-0.17

 alike

-0.15

zÃ¡

-0.14

udio

-0.14

Ses

-0.14

elen

-0.14

è¿Ļä¸Ģ

-0.14

 váºŃy

-0.13

POSITIVE LOGITS

StackNavigator

0.15

estate

0.15

egis

0.15

ãĥ¼ãĥ«

0.15

ĶåĽŀ

0.15

abis

0.15

alles

0.15

PATCH

0.15

oola

0.14

#echo

0.14

Activations Density 0.126%

instances of significant emotional expressions or personal reflections

No Comments

No Known Activations