INDEX

Explanations

references to specific entities or organizations, particularly those related to educational institutions or programs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

olen

-0.19

ugged

-0.16

Bew

-0.15

à¸¡à¸Ń

-0.14

agma

-0.14

odega

-0.14

onn

-0.14

onomous

-0.14

ugal

-0.14

 Bere

-0.14

POSITIVE LOGITS

 Legs

0.14

rics

0.14

ibraltar

0.14

MBED

0.13

ilib

0.13

xiv

0.13

erties

0.13

dru

0.13

tes

0.13

med

0.13

Activations Density 0.032%

references to specific entities or organizations, particularly those related to educational institutions or programs

No Comments

No Known Activations