INDEX

Explanations

references to film production elements, particularly related to sets and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oupon

-0.15

anke

-0.15

Ã¤nge

-0.15

ANTED

-0.15

å·±

-0.14

 carriage

-0.14

swe

-0.14

_PG

-0.14

/setup

-0.13

MK

-0.13

POSITIVE LOGITS

aqu

0.18

esan

0.17

\Collections

0.15

 lÃłng

0.15

Ã½Å¡

0.14

sbin

0.14

jee

0.14

urre

0.14

oji

0.14

\Has

0.14

Activations Density 0.020%

references to film production elements, particularly related to sets and design

No Comments

No Known Activations