INDEX

Explanations

high-frequency function words and specific phrases indicating emphasis or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

chl

-0.19

edin

-0.18

annel

-0.15

à¸Ķà¸£

-0.15

Ãłn

-0.15

OnError

-0.14

.onNext

-0.14

æ¶

-0.14

 OnCollision

-0.14

shan

-0.14

POSITIVE LOGITS

GLOBALS

0.15

ATS

0.14

Ro

0.14

uy

0.14

oe

0.14

 Katy

0.14

erson

0.14

 conv

0.14

atÃ³

0.14

Activations Density 0.000%

high-frequency function words and specific phrases indicating emphasis or intensity

No Comments

No Known Activations