INDEX

Explanations

references to social events or gatherings

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

unce

-0.17

á»ĳng

-0.16

Kel

-0.16

éłĵ

-0.15

zyst

-0.15

ìŀħ

-0.15

 bead

-0.15

verted

-0.14

ppard

-0.14

apor

-0.14

POSITIVE LOGITS

 Voor

0.17

yas

0.15

ader

0.15

ears

0.15

UTH

0.15

ore

0.14

oref

0.14

uth

0.14

eref

0.14

æĪ

0.13

Activations Density 0.001%

references to social events or gatherings

No Comments

No Known Activations