INDEX

Explanations

phrases and concepts related to relevance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ston

-0.17

maal

-0.16

ecycle

-0.15

rador

-0.14

 finalize

-0.14

LOBAL

-0.14

ymes

-0.13

ov

-0.13

ayo

-0.13

mdi

-0.13

POSITIVE LOGITS

oles

0.17

ening

0.15

etÃŃ

0.15

etrics

0.15

ubit

0.15

Ã¾

0.15

ekce

0.14

les

0.14

 WithEvents

0.14

etter

0.14

Activations Density 0.014%

phrases and concepts related to relevance or significance

No Comments

No Known Activations