INDEX

Explanations

expressions of emotional experiences and reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 attract

-0.18

 attracted

-0.15

ple

-0.15

 Shapes

-0.15

uite

-0.15

avou

-0.15

 ÑĥÐ´Ð¸Ð²

-0.14

unp

-0.14

 à¤Ĩà¤ķà¤°

-0.14

 attractiveness

-0.14

POSITIVE LOGITS

 leave

0.22

 send

0.21

 left

0.20

 sends

0.19

 leaving

0.19

leave

0.19

 leaves

0.18

left

0.18

 Send

0.18

Send

0.18

Activations Density 0.124%

expressions of emotional experiences and reflections

No Comments

No Known Activations