INDEX

Explanations

references to California

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

.scalablytyped

-0.16

ÃĹ↵↵

-0.16

-calendar

-0.15

Calendar

-0.14

uo

-0.14

ylum

-0.14

uelle

-0.14

ÑģÑı

-0.14

uj

-0.14

POSITIVE LOGITS

iforn

0.26

ifornia

0.24

 dreaming

0.22

 State

0.19

 Governor

0.19

aver

0.19

 Penal

0.18

 Poly

0.18

å·ŀ

0.17

 Dream

0.17

Activations Density 0.016%

references to California

No Comments

No Known Activations