INDEX

Explanations

mentions of educational recognitions and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Lancaster

-0.16

Mot

-0.15

uelle

-0.15

tog

-0.15

nec

-0.14

etroit

-0.14

dy

-0.14

rz

-0.14

PDF

-0.14

 receiver

-0.14

POSITIVE LOGITS

 suburb

0.19

 Burl

0.18

 suburban

0.18

ausal

0.17

 Bethesda

0.17

 village

0.16

 affluent

0.16

Ð°Ð»ÐµÐ¶

0.16

 Brent

0.16

taire

0.15

Activations Density 0.342%

mentions of educational recognitions and awards

No Comments

No Known Activations