INDEX

Explanations

references to inter-community interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

vron

-0.18

ertas

-0.17

elow

-0.17

skyt

-0.16

rage

-0.16

sonian

-0.16

 ÐºÐ°Ñģ

-0.15

åĪ¶

-0.15

urd

-0.14

arness

-0.14

POSITIVE LOGITS

 inter

0.19

 Inter

0.18

iors

0.18

/in

0.18

-inter

0.17

.Inter

0.16

 Milan

0.16

inter

0.16

oute

0.16

ationale

0.16

Activations Density 0.021%

references to inter-community interactions

No Comments

No Known Activations