INDEX

Explanations

action verbs that indicate movement or change

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

venta

-0.19

uki

-0.18

 apart

-0.17

ango

-0.15

 link

-0.15

aku

-0.14

uk

-0.14

 ìĺģêµŃ

-0.14

elope

-0.14

tail

-0.14

POSITIVE LOGITS

 round

0.40

round

0.26

 ROUND

0.24

 Round

0.24

.round

0.23

Round

0.22

(round

0.22

_ROUND

0.21

-round

0.21

_round

0.18

Activations Density 0.199%

action verbs that indicate movement or change

No Comments

No Known Activations