INDEX

Explanations

words related to notable individuals or entities associated with the themes of endings and transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

er

-0.22

erie

-0.19

erable

-0.18

erne

-0.18

quez

-0.18

erot

-0.17

andbox

-0.17

sent

-0.17

erk

-0.17

eru

-0.17

POSITIVE LOGITS

ele

0.25

igo

0.25

eb

0.23

ez

0.22

ev

0.22

IGO

0.21

ee

0.21

el

0.21

ell

0.20

Activations Density 0.018%

words related to notable individuals or entities associated with the themes of endings and transitions

No Comments

No Known Activations