INDEX

Explanations

expressions of belief and self-worth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

dea

-0.18

alent

-0.16

ĭ

-0.16

ãģ°ãģĭãĤĬ

-0.15

utz

-0.15

yh

-0.14

aru

-0.14

rak

-0.14

vik

-0.14

quel

-0.14

POSITIVE LOGITS

 strongly

0.28

fully

0.20

 firmly

0.19

lessly

0.19

 whole

0.17

fulness

0.17

 passionately

0.17

whole

0.17

ance

0.16

 otherwise

0.16

Activations Density 0.047%

expressions of belief and self-worth

No Comments

No Known Activations