INDEX

Explanations

phrases related to community events and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Indian

-0.18

 Wald

-0.17

agini

-0.17

å½

-0.16

urga

-0.15

ilio

-0.15

 Indians

-0.15

 Halk

-0.14

 winters

-0.14

 Sage

-0.14

POSITIVE LOGITS

 Liberia

0.21

 Paramount

0.17

 cocoa

0.15

 Dias

0.15

GNU

0.15

phia

0.15

ISODE

0.15

ambia

0.15

 Liber

0.14

Activations Density 0.042%

phrases related to community events and interactions

No Comments

No Known Activations