INDEX

Explanations

questions and inquiries, particularly those starting with "Does."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ster

-0.17

icens

-0.16

iously

-0.16

èĬĿ

-0.15

 nett

-0.15

avis

-0.15

kses

-0.15

ÑĢÐµÐ¶

-0.14

hou

-0.14

 Sterling

-0.14

POSITIVE LOGITS

OTS

0.15

bish

0.15

eyle

0.14

aura

0.14

ITS

0.14

 Edwin

0.14

ARA

0.14

tap

0.14

intros

0.13

engin

0.13

Activations Density 0.038%

questions and inquiries, particularly those starting with "Does."

No Comments

No Known Activations