INDEX

Explanations

instances of significant actions or outcomes within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

dit

-0.17

iaux

-0.15

riel

-0.15

amp

-0.15

Ã©rie

-0.14

RIES

-0.14

 needless

-0.14

Ã¶rÃ¼

-0.14

 whereas

-0.14

NB

-0.13

POSITIVE LOGITS

 respectively

0.15

 dare

0.15

adh

0.15

nay

0.15

via

0.14

oh

0.14

or

0.14

åīĩ

0.14

{},

0.14

Activations Density 0.369%

instances of significant actions or outcomes within a context

No Comments

No Known Activations