INDEX

Explanations

references to pairs or groups of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

onda

-0.21

all

-0.20

-0.16

 various

-0.16

relationships

-0.16

obar

-0.16

 relationships

-0.15

iera

-0.15

idding

-0.14

È

-0.14

POSITIVE LOGITS

-two

0.26

 beiden

0.26

 beide

0.25

ä¸¤ä¸ª

0.24

two

0.24

åĪĨåĪ«

0.23

 ambos

0.23

 obou

0.23

 Both

0.23

 halves

0.23

Activations Density 0.408%

references to pairs or groups of entities

No Comments

No Known Activations