INDEX

Explanations

names and references related to individuals and organizations involved in design and architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 global

-0.15

ÑĤÐ¾Ð³Ð¾

-0.15

igned

-0.15

Ð»ÐµÐ³

-0.15

Minor

-0.15

ockets

-0.14

minor

-0.14

Ã©gorie

-0.14

Global

-0.14

sen

-0.14

POSITIVE LOGITS

à¹Ģà¸ĭ

0.15

omap

0.15

 local

0.14

hic

0.13

.mit

0.13

huy

0.13

·æĸ°

0.13

essim

0.13

leich

0.13

 indigenous

0.13

Activations Density 0.326%

names and references related to individuals and organizations involved in design and architecture

No Comments

No Known Activations