INDEX

Explanations

references to perspectives and observations on systemic issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

essen

-0.19

ativ

-0.16

ffd

-0.15

umat

-0.15

bage

-0.15

lich

-0.15

ureka

-0.15

olio

-0.14

inals

-0.14

als

-0.14

POSITIVE LOGITS

 merely

0.28

 simply

0.20

åıªæĺ¯

0.18

-selector

0.17

à¹ģà¸Ħ

0.17

 instead

0.17

nor

0.16

 juste

0.16

 just

0.16

nor

0.16

Activations Density 0.097%

references to perspectives and observations on systemic issues

No Comments

No Known Activations