INDEX

Explanations

discussions related to performance and achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ayan

-0.17

omorphic

-0.16

zell

-0.15

illo

-0.14

entionPolicy

-0.14

ÑĭÐ²Ð°Ð½Ð¸Ñı

-0.13

ayla

-0.13

illance

-0.13

Ans

-0.13

lech

-0.13

POSITIVE LOGITS

otti

0.18

otle

0.16

thag

0.16

cono

0.15

 Howe

0.14

 Dirt

0.14

.opendaylight

0.14

mith

0.14

ed

0.14

Activations Density 0.063%

discussions related to performance and achievement

No Comments

No Known Activations