INDEX

Explanations

first-person perspectives and personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ð³Ð°Ð»

-0.16

Ã¹i

-0.15

zee

-0.15

ycz

-0.14

 Sabha

-0.14

ÙĬÙĩ

-0.14

Ngh

-0.14

ulti

-0.14

die

-0.14

quisite

-0.14

POSITIVE LOGITS

UY

0.18

 bracket

0.15

AffineTransform

0.14

 honor

0.14

 favor

0.14

_HW

0.14

Î¼Î¼

0.14

 recently

0.14

Ī

0.14

Activations Density 0.321%

first-person perspectives and personal reflections

No Comments

No Known Activations