INDEX

Explanations

references to specific geographic locations and organizations involved in community activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ã¨m

-0.16

hta

-0.15

ARK

-0.15

AllWindows

-0.14

 Caval

-0.13

PLIER

-0.13

ÙĬÙģ

-0.13

abox

-0.13

ark

-0.13

ount

-0.13

POSITIVE LOGITS

ounge

0.15

usalem

0.15

ulary

0.14

LAG

0.14

usa

0.14

 hold

0.14

-sidebar

0.14

Ã¼f

0.13

 chip

0.13

ÑĢÑĥÑĤ

0.13

Activations Density 0.128%

references to specific geographic locations and organizations involved in community activities

No Comments

No Known Activations