INDEX

Explanations

concepts related to complexity and diversity in perspectives or experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ova

-0.15

loat

-0.15

 installations

-0.15

igy

-0.14

 orient

-0.14

ibel

-0.13

inen

-0.13

antee

-0.13

 predicate

-0.13

lek

-0.13

POSITIVE LOGITS

 voices

0.24

 cultures

0.20

 competing

0.19

 Voices

0.18

 identities

0.18

 hats

0.18

.scalablytyped

0.17

çļĦå£°éŁ³

0.17

 equally

0.16

 worlds

0.16

Activations Density 0.186%

concepts related to complexity and diversity in perspectives or experiences

No Comments

No Known Activations