INDEX

Explanations

phrases that highlight challenges or complications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Mori

-0.16

awa

-0.16

eland

-0.15

ìĿµ

-0.15

orie

-0.15

yle

-0.14

 ÃĩaÄŁ

-0.14

ASA

-0.14

obil

-0.14

ymi

-0.14

POSITIVE LOGITS

atrix

0.14

olley

0.14

yro

0.14

ollo

0.13

 least

0.13

OSP

0.13

Uvs

0.13

_miss

0.13

cxx

0.13

Activations Density 0.066%

phrases that highlight challenges or complications in various contexts

No Comments

No Known Activations