INDEX

Explanations

expressions of disappointment or lack of engagement with media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãĥ³ãĤº

-0.15

Å¡li

-0.13

iteur

-0.13

foy

-0.13

hev

-0.13

aira

-0.13

zimmer

-0.13

sworth

-0.13

zie

-0.13

à¸º

-0.13

POSITIVE LOGITS

åł

0.14

aven

0.13

 Edwin

0.13

cient

0.13

Ð»ÐµÑĢ

0.13

fol

0.13

ffen

0.13

diÄŁi

0.13

omor

0.12

Activations Density 0.305%

expressions of disappointment or lack of engagement with media

No Comments

No Known Activations