INDEX

Explanations

numerical values, particularly related to years and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

illard

-0.14

izzo

-0.14

 Foreign

-0.14

iframe

-0.14

alsa

-0.14

ilon

-0.13

allax

-0.13

ÑĪÐºÐ°

-0.13

EGA

-0.13

Ø

-0.13

POSITIVE LOGITS

eson

0.16

ãģ£ãģ±

0.15

ead

0.14

things

0.14

ris

0.14

swire

0.14

zbollah

0.13

áº»

0.13

inic

0.13

&gt

0.13

Activations Density 0.017%

numerical values, particularly related to years and measurements

No Comments

No Known Activations