INDEX

Explanations

second-person pronouns and related phrases indicating personal experience or direct address

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Kron

-0.15

uslim

-0.14

ÐºÐ°Ð²

-0.14

shaw

-0.14

.dw

-0.14

ittest

-0.14

ypsum

-0.14

ÑģÑĮ

-0.14

ourke

-0.13

ISCO

-0.13

POSITIVE LOGITS

 found

0.36

 find

0.35

 finds

0.34

found

0.32

 finding

0.31

 finden

0.30

 encontrar

0.30

æī¾åĪ°

0.29

 Find

0.29

(find

0.28

Activations Density 0.074%

second-person pronouns and related phrases indicating personal experience or direct address

No Comments

No Known Activations