INDEX

Explanations

contexts related to sharing and various forms of dependency or obligation in relationships

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

raki

-0.16

ascus

-0.15

ritel

-0.14

alara

-0.14

åĲ¾

-0.14

ØŁØŁ

-0.14

skl

-0.14

minate

-0.14

riel

-0.14

erras

-0.14

POSITIVE LOGITS

0.15

.+

0.14

 spur

0.14

 Blink

0.13

tie

0.13

´

0.13

 depending

0.13

Ms

0.13

Activations Density 0.017%

contexts related to sharing and various forms of dependency or obligation in relationships

No Comments

No Known Activations