INDEX

Explanations

references to specific entities or concepts, particularly related to media, culture, and organizational structures

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

orman

-0.18

reh

-0.18

orry

-0.15

dej

-0.15

roat

-0.14

aille

-0.14

ansa

-0.14

otos

-0.14

rena

-0.14

chedulers

-0.14

POSITIVE LOGITS

ì²ľ

0.14

ÑģÑĤÐ²

0.14

dil

0.14

 prelim

0.14

 mock

0.14

 disc

0.13

 ours

0.13

Ð»ÐµÑĢ

0.13

_mock

0.13

ErrorException

0.13

Activations Density 1.169%

references to specific entities or concepts, particularly related to media, culture, and organizational structures

No Comments

No Known Activations