INDEX

Explanations

phrases indicating interpersonal relationships and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

iland

-0.18

 myself

-0.15

inite

-0.14

ç»ĻæĪĳ

-0.14

 ours

-0.14

kea

-0.14

à¹īà¸Ńà¸¢

-0.13

MBProgressHUD

-0.13

kad

-0.13

_nv

-0.13

POSITIVE LOGITS

irler

0.16

iral

0.15

dera

0.14

 ÑĪÑĤ

0.14

ira

0.14

ipur

0.14

entin

0.14

icom

0.14

riott

0.14

ahr

0.13

Activations Density 0.244%

phrases indicating interpersonal relationships and conflicts

No Comments

No Known Activations