INDEX

Explanations

words related to performance metrics and evaluation 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

ingly

-0.18

lijk

-0.15

tin

-0.14

ÉĻ

-0.14

ekli

-0.14

hid

-0.14

inner

-0.14

Ly

-0.14

.ly

-0.14

ignon

-0.14

POSITIVE LOGITS

azzo

0.15

vale

0.14

-vars

0.14

typings

0.14

)((((

0.14

oppel

0.14

ulty

0.14

isoft

0.14

 marc

0.14

Smarty

0.14

Activations Density 0.600%

words related to performance metrics and evaluation in various contexts

No Comments

No Known Activations