INDEX

Explanations

terms related to social media and public engagement roles or responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Oregon

-0.23

Oregon

-0.20

 Arkansas

-0.20

 Kyoto

-0.19

 Portland

-0.19

 Wichita

-0.18

 Kansas

-0.18

ogle

-0.18

 Montana

-0.18

Portland

-0.17

POSITIVE LOGITS

Lyn

0.39

 Nass

0.39

 Suffolk

0.34

 village

0.33

 Village

0.32

LI

0.29

 Hemp

0.29

 Beach

0.26

Isl

0.26

LI

0.26

Activations Density 0.004%

terms related to social media and public engagement roles or responsibilities

No Comments

No Known Activations