INDEX

Explanations

phrases indicating the allocation or prioritization of importance or value

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

zeug

-0.16

opup

-0.15

trag

-0.15

/from

-0.15

 Avec

-0.15

ecz

-0.15

ape

-0.14

illy

-0.14

atsu

-0.14

 apply

-0.14

POSITIVE LOGITS

 emphasis

0.30

 bets

0.29

 importance

0.23

 blame

0.23

emphasis

0.23

 Importance

0.21

 emphasize

0.19

 demands

0.19

 placed

0.18

 Limits

0.18

Activations Density 0.044%

phrases indicating the allocation or prioritization of importance or value

No Comments

No Known Activations