INDEX

Explanations

references to significant emotional events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

earer

-0.14

apid

-0.14

erule

-0.13

erli

-0.13

isser

-0.13

ÑĤÐ¾Ð¼

-0.12

ardon

-0.12

à¸£à¸ĵ

-0.12

 Setter

-0.12

.Warn

-0.12

POSITIVE LOGITS

 survived

0.45

 survive

0.44

 survives

0.41

 escape

0.41

 escaped

0.40

 escapes

0.39

 avoided

0.38

 Surv

0.38

 surviv

0.37

 avoid

0.35

Activations Density 0.342%

references to significant emotional events or experiences

No Comments

No Known Activations