INDEX

Explanations

phrases related to participation and involvement in events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ø§Ø³ÙĬ

-0.17

loh

-0.15

 Choice

-0.15

apon

-0.15

ukan

-0.14

eries

-0.14

pagen

-0.14

ellen

-0.14

orie

-0.13

POSITIVE LOGITS

resh

0.16

dl

0.15

ÃĿ

0.14

Ø·ÙĨ

0.14

 help

0.14

utsch

0.14

stood

0.14

cret

0.14

ients

0.13

ingroup

0.13

Activations Density 0.087%

phrases related to participation and involvement in events

No Comments

No Known Activations