INDEX

Explanations

words and concepts related to emotional expressions and responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

annya

-0.17

ependency

-0.16

inery

-0.16

ediÄŁi

-0.15

eton

-0.15

unner

-0.15

ucch

-0.15

esser

-0.15

aversal

-0.15

Ã¡tka

-0.15

POSITIVE LOGITS

less

0.17

Smy

0.17

lyn

0.15

nel

0.15

amine

0.15

IDL

0.15

ores

0.14

æ³ģ

0.14

ized

0.14

rans

0.14

Activations Density 0.040%

words and concepts related to emotional expressions and responses

No Comments

No Known Activations