INDEX

Explanations

references to past experiences or historical context in various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Second

-0.17

 ensuing

-0.14

antic

-0.14

 Third

-0.13

 forthcoming

-0.13

jej

-0.13

igo

-0.13

itest

-0.13

à¸±à¸¨

-0.13

PS

-0.13

POSITIVE LOGITS

 first

0.80

first

0.69

.first

0.51

	first

0.49

 eerste

0.48

(first

0.47

 primeiro

0.46

 poprvÃ©

0.46

-first

0.45

 ersten

0.45

Activations Density 0.376%

references to past experiences or historical context in various topics

No Comments

No Known Activations

references to past experiences or historical context in various topics

No Comments

No Known Activations