INDEX

Explanations

concepts related to academic roles and research interests in various fields, particularly those involving social sciences and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

.protobuf

-0.16

etus

-0.15

ÃŃky

-0.15

à¸°

-0.14

aly

-0.14

-0.13

osti

-0.13

ÐµÑı

-0.13

Hud

-0.13

Adv

-0.13

POSITIVE LOGITS

 theory

0.25

 Theory

0.19

 studies

0.18

 Studies

0.18

theory

0.17

vs

0.17

 versus

0.16

çĲĨè®º

0.16

gone

0.16

Studies

0.16

Activations Density 0.362%

concepts related to academic roles and research interests in various fields, particularly those involving social sciences and community engagement

No Comments

No Known Activations