INDEX

Explanations

references to individuals and notable figures in the context of discussion or reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

amburg

-0.16

lag

-0.15

 Mush

-0.15

uki

-0.14

 Wheel

-0.14

avadoc

-0.14

redient

-0.14

omu

-0.14

rices

-0.13

abox

-0.13

POSITIVE LOGITS

kas

0.16

agate

0.15

ç«¥

0.14

opal

0.14

 CASCADE

0.14

 Vish

0.14

ndl

0.14

ŀ

0.14

opl

0.13

Ros

0.13

Activations Density 0.193%

references to individuals and notable figures in the context of discussion or reporting

No Comments

No Known Activations