INDEX

Explanations

references to indigenous identity and heritage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rij

-0.17

ohl

-0.16

naire

-0.16

loff

-0.16

kel

-0.16

ÑģÑı

-0.15

ishments

-0.15

ulf

-0.15

tails

-0.15

enk

-0.15

POSITIVE LOGITS

-born

0.29

born

0.24

 born

0.21

 tongue

0.21

/local

0.20

/original

0.19

-spe

0.19

 speaker

0.19

 Born

0.19

 Hawaiian

0.18

Activations Density 0.016%

references to indigenous identity and heritage

No Comments

No Known Activations