INDEX

Explanations

references to pairs or groups of entities or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

all

-0.20

æīĢæľī

-0.17

 various

-0.15

 Ð²ÑģÐµÑħ

-0.15

Of

-0.15

 wasn

-0.15

-0.14

 Various

-0.14

onda

-0.14

 itself

-0.14

POSITIVE LOGITS

 alike

0.30

 respectively

0.24

 respective

0.21

 equally

0.20

 Äĳá»ģu

0.19

 birden

0.19

 separately

0.18

 sets

0.15

chin

0.15

vero

0.14

Activations Density 0.155%

references to pairs or groups of entities or subjects

No Comments

No Known Activations