INDEX

Explanations

terms related to participation and involvement in activities or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

en

-0.15

gan

-0.15

Key

-0.15

å¤

-0.15

IDL

-0.14

uo

-0.14

anine

-0.14

uary

-0.13

 ware

-0.13

POSITIVE LOGITS

estar

0.18

lesia

0.17

irl

0.16

essaging

0.15

ilton

0.15

kontakte

0.14

ysize

0.14

orderby

0.14

riba

0.14

onet

0.14

Activations Density 0.118%

terms related to participation and involvement in activities or programs

No Comments

No Known Activations