INDEX

Explanations

expressions of interpersonal relationships and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iggs

-0.17

allen

-0.15

inho

-0.15

aku

-0.14

Å¡tÄĽ

-0.14

ç§

-0.14

lew

-0.14

.hw

-0.14

imoto

-0.13

POSITIVE LOGITS

 well

0.58

well

0.44

 better

0.40

 dobÅĻe

0.38

 WELL

0.37

 bien

0.37

 poorly

0.36

 mieux

0.35

Well

0.35

 Well

0.34

Activations Density 0.257%

expressions of interpersonal relationships and well-being

No Comments

No Known Activations