INDEX

Explanations

expressions related to honoring or remembering individuals or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ARAM

-0.18

aram

-0.17

aggi

-0.16

uvo

-0.15

haust

-0.15

isay

-0.15

DAQ

-0.15

.toolbox

-0.15

alim

-0.14

ÏĥÏĦÎµ

-0.14

POSITIVE LOGITS

 pend

0.17

inc

0.17

eps

0.17

AMA

0.16

lasses

0.16

esz

0.15

-inc

0.15

/rs

0.15

ink

0.14

Activations Density 0.012%

expressions related to honoring or remembering individuals or events

No Comments

No Known Activations