INDEX

Explanations

phrases that establish conditions or implications regarding various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

gili

-0.17

ynn

-0.16

iveau

-0.16

UTH

-0.15

zem

-0.15

esse

-0.14

ansa

-0.14

 fisse

-0.14

istencia

-0.14

efs

-0.14

POSITIVE LOGITS

ÏħÏĢ

0.16

arrow

0.16

Äįas

0.14

ish

0.13

ÑıÐ³

0.13

agar

0.13

LPC

0.13

)./

0.13

Activations Density 0.050%

phrases that establish conditions or implications regarding various situations

No Comments

No Known Activations