INDEX

Explanations

the name "Lauren" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Dank

-0.17

structor

-0.16

anka

-0.16

lun

-0.15

hurst

-0.15

nova

-0.14

çħ§

-0.14

halt

-0.14

_drawer

-0.14

vergence

-0.14

POSITIVE LOGITS

ames

0.16

unched

0.16

±Ð¾ÑĤ

0.15

 Mage

0.15

aub

0.14

enge

0.14

ousse

0.14

ats

0.14

rosse

0.14

Activations Density 0.082%

the name "Lauren" and its variations

No Comments

No Known Activations