INDEX

Explanations

reflexive verbs indicating actions taken by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

se

-0.24

omen

-0.18

.fits

-0.17

arks

-0.17

pars

-0.16

props

-0.15

Ð°Ð½Ð½Ñĸ

-0.14

ÙĪÙĨÛĮ

-0.14

 Diabetes

-0.14

itur

-0.14

POSITIVE LOGITS

 udÃ¡l

0.19

 suic

0.16

 comport

0.15

opard

0.15

 crash

0.15

LAR

0.14

 profil

0.14

 Lamb

0.13

 concentr

0.13

áº

0.13

Activations Density 0.017%

reflexive verbs indicating actions taken by individuals

No Comments

No Known Activations