INDEX

Explanations

actions and expressions related to observational interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

aida

-0.17

ilet

-0.16

ium

-0.16

 Laud

-0.16

aud

-0.15

icio

-0.15

pio

-0.15

steen

-0.14

ksi

-0.14

elper

-0.14

POSITIVE LOGITS

 Sanford

0.15

Ð¡Ðŀ

0.14

 Funding

0.14

icken

0.13

ÏĦÎ¿Ïħ

0.13

yling

0.13

ÏĬÎº

0.13

CDATA

0.13

ç¦ı

0.13

 Ð¾Ñĩ

0.13

Activations Density 0.157%

actions and expressions related to observational interactions between characters

No Comments

No Known Activations