INDEX

Explanations

concepts and discussions related to representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÌĢ

-0.16

aday

-0.16

çļ

-0.15

lington

-0.15

 trÆ°á»Łng

-0.15

.epam

-0.15

itten

-0.14

ova

-0.14

ContentView

-0.14

olan

-0.14

POSITIVE LOGITS

 ÑģÐ¾Ð±Ð¾Ð¹

0.21

 Representative

0.16

Represent

0.16

 representative

0.15

Ãºblica

0.15

represent

0.15

acted

0.14

asser

0.14

ational

0.14

_RA

0.14

Activations Density 0.026%

concepts and discussions related to representation

No Comments

No Known Activations