INDEX

Explanations

phrases indicating frequency or typicality of actions and characteristics associated with women

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 possibly

-0.25

 sometimes

-0.24

 potentially

-0.23

 occasionally

-0.21

sometimes

-0.20

 Sometimes

-0.20

possibly

-0.20

 Ð¸Ð½Ð¾Ð³Ð´Ð°

-0.18

 Possibly

-0.18

Sometimes

-0.17

POSITIVE LOGITS

 either

0.27

either

0.22

 Either

0.21

 bÃ½

0.20

 unless

0.20

 Ð»Ð¸Ð±Ð¾

0.19

Either

0.19

 EITHER

0.19

 accompanies

0.18

 accompanied

0.16

Activations Density 0.487%

phrases indicating frequency or typicality of actions and characteristics associated with women

No Comments

No Known Activations