INDEX

Explanations

references to testing frameworks and processes

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

Ã¢y

-0.15

isz

-0.15

ÌĢ

-0.14

reak

-0.14

ipers

-0.14

ETA

-0.14

 Ã¢

-0.13

et

-0.13

ongan

-0.13

POSITIVE LOGITS

/renderer

0.18

Convertible

0.15

AndView

0.14

 Morrow

0.14

:animated

0.14

boz

0.14

Brains

0.13

à¥ĭà¤·à¤£

0.13

TRS

0.13

(iOS

0.13

Activations Density 0.183%

references to testing frameworks and processes

No Comments

No Known Activations