INDEX

Explanations

concepts related to language learning and instructional methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ushi

-0.16

 Lair

-0.15

agens

-0.15

Ã¡nh

-0.15

IFF

-0.14

 Ø´Ø¨

-0.14

Artifact

-0.14

çĪ

-0.14

isin

-0.14

å¹ķ

-0.14

POSITIVE LOGITS

 Listening

0.21

 communic

0.21

 Cambridge

0.21

 listening

0.21

 Pron

0.20

 Grammar

0.19

 Teacher

0.18

 Intermediate

0.18

 Activities

0.17

listening

0.17

Activations Density 0.019%

concepts related to language learning and instructional methods

No Comments

No Known Activations