INDEX

Explanations

references to personal connections and networking opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãĥŃãĥ¼

-0.17

CLAIM

-0.15

ksam

-0.15

agna

-0.15

leep

-0.15

mayan

-0.14

_Impl

-0.14

adel

-0.14

agne

-0.14

etry

-0.14

POSITIVE LOGITS

 networks

0.23

 network

0.22

network

0.20

 Networks

0.20

 NETWORK

0.18

 networking

0.18

 Network

0.17

 rÃ©seau

0.16

-network

0.15

 sparing

0.15

Activations Density 0.071%

references to personal connections and networking opportunities

No Comments

No Known Activations