INDEX

Explanations

references to company positions and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 mist

-0.16

sz

-0.15

anut

-0.15

sa

-0.15

åºľ

-0.15

zone

-0.15

 Disorder

-0.15

acher

-0.15

 Trouble

-0.14

elsey

-0.14

POSITIVE LOGITS

 Geile

0.19

 parent

0.18

 EntryPoint

0.18

Regions

0.18

Republic

0.17

Signature

0.17

vX

0.17

tru

0.16

HDR

0.16

 Regions

0.16

Activations Density 0.313%

references to company positions and roles

No Comments

No Known Activations